From 4d582975e49a82818fadf961f26bc0fd2ccf4af4 Mon Sep 17 00:00:00 2001 From: Troyanov Daniil Date: Tue, 9 Dec 2025 10:51:34 +0300 Subject: [PATCH] LW 3 done --- labworks/LW3/2.png | Bin 0 -> 315 bytes labworks/LW3/7.png | Bin 0 -> 273 bytes labworks/LW3/best_mnist_model.keras | Bin 0 -> 46150 bytes labworks/LW3/images/1.png | Bin 0 -> 7089 bytes labworks/LW3/images/2.png | Bin 0 -> 7138 bytes labworks/LW3/images/3.png | Bin 0 -> 31877 bytes labworks/LW3/images/4.png | Bin 0 -> 6902 bytes labworks/LW3/images/5.png | Bin 0 -> 6711 bytes labworks/LW3/images/6.png | Bin 0 -> 123991 bytes labworks/LW3/images/7.png | Bin 0 -> 11366 bytes labworks/LW3/images/8.png | Bin 0 -> 12579 bytes labworks/LW3/images/9.png | Bin 0 -> 62707 bytes labworks/LW3/lab3_new.ipynb | 1680 +++++++++++++++++++++++++++ labworks/LW3/report_new.md | 612 ++++++++++ 14 files changed, 2292 insertions(+) create mode 100644 labworks/LW3/2.png create mode 100644 labworks/LW3/7.png create mode 100644 labworks/LW3/best_mnist_model.keras create mode 100644 labworks/LW3/images/1.png create mode 100644 labworks/LW3/images/2.png create mode 100644 labworks/LW3/images/3.png create mode 100644 labworks/LW3/images/4.png create mode 100644 labworks/LW3/images/5.png create mode 100644 labworks/LW3/images/6.png create mode 100644 labworks/LW3/images/7.png create mode 100644 labworks/LW3/images/8.png create mode 100644 labworks/LW3/images/9.png create mode 100644 labworks/LW3/lab3_new.ipynb create mode 100644 labworks/LW3/report_new.md diff --git a/labworks/LW3/2.png b/labworks/LW3/2.png new file mode 100644 index 0000000000000000000000000000000000000000..f7058b72f832b4ee68433f795121500968664a99 GIT binary patch literal 315 zcmeAS@N?(olHy`uVBq!ia0vp^G9b*s1SJ3FdmIK*jKx9jP7LeL$-D$|SkfJR9T^xl z_H+M9WCij$3p^r=85sD03i%E*9?xHq0u;R9>EamT;r({1A>UyI9@oWwGQG(uX9PDD zF}a0plhIB-*3)xkQoW$BXEw_!k*)chzi!yeFR?g0|NX+Pao0_!Db&iiUpc9Gy!QUX zK&6&|x4Uztcb!*^5Aj|w<3;yHOZKk^ZO-557M#>#qqZbnL;3wBZiQNvuX~QAtl1h9 zP{>?!z}VeM^XM{`C1uMpn^N5`m%Kc^$swyw$9_ygYaLdPW5uvEO?xQp*_0lV^EamT;r(`sHP;aZ5m(*VSxZkBaK1aD z8nH{o8wj2Y3=#dO|wg1_(u^%-glf8dcP?xv@BVW7uSZ_iLy-)^8rk1;VCXKG?L)@ZDW z*|>4t)&1O83Go%uod2C>hCMVP*Pqdt5)c#?YS&%yFZy}7hkE+B3I+e{s`D>J#*Q;t zC~V?40Ghv*?^ZF$JvgKrmBsFUA>AkiyDwStb4Y&|{KnU}Tcqnxh5i@47Ix^r-V1B* z0HN&e&i(u0^!iQvzdw@QgA^9v8`?caqm6_ach6AYaQD!jDG?I5IMm;LWp_WqLcCo) zeBHYldyGzK%>mwiuD-(RLeuqKEgZ1_zyb~bi5~J3kU!b}WWT`Rz)+_E-^GE!{(r$M z#QW!Hbq{p6p8v5ec2m0b`rp)Jfp>7=FZKR0UjJ*EJ-rty73Sw2+|&D>$?;R4|B%vC zOK21!KLr_!ei`zAFh$m_Tlf$Df6eqSLHp{A}Vy_ zM&`e+v183l#u=NAGZref!rOO=PpGSxx2OB6f5Y9=&o?Nb+xY%55=;C7J>30V|2?6* zB;4IEtXoFUsC7>ZZ+~}T!EdJ`%(?mp`U@R;Sa+L7hUVr%+1;gq!o_Aqu&;1!SseV+ zqYGW|KN|826s`y%p6)`>77Hg~VE1I|k+CG$-OE?lo~yg3XPCdx+`6ZytI#b6b{*&ux?&sH!o~yfl_w_sfE63xx_1uW`qzOG~ zx#+JO5nlHnk2kQVT)wCMzw$ZGwz1&}Ie)kRJMF2)YnS+SC-uAF@AQ8Z0=702W_EXY zUQe%ed(smSg$o~Ty6=BIMDck4aGyO4zwOlMcZL5X72%2f$$sT}>{nO#K-+z} z{ru+fe%bH8&5ys@Zx7qw$^TFU{%XI!{a8YeU;7QqZ~Odd?7s{DH&O@t8P?r4-0l0j zuLR{^>2EnTJ^2eNzsi66=@W&2=6lnVmn;5N{#$=_u|MtBfd#=U#NP3Z9<-DQ)lX4w6t^$gTM z^9jkke|yvI&hdD^-QI7Qf4({i%X{GeM=E>}{K^0Ot5Ej$-QVfo2>gw}-w6DTz~2b` zjlkas{Efih2>gw}-w6DTz~2b`jllnD1pZZ={IBtu|13@}HRPA(zvDCir~C1@y#Koh z{58(_JMQuXg-fkH6DDBk-^G%jRkR;&ba^ z|Ihq@ZNV?b-~Owo+TY3l5Cs0}2Y&BM9Z>%>07gC8(LL$!`8xj3Z2#rlU;V&LwO>_# zx4W_@pQHX?Zt{O50*1h-Dz2Ek8OnL@Jgs1xxXA#j~1#&$b zVZRQx2+zL!B`+pCk(bpyDG_M>La zR=Byqm&&B*WBRD|n4(eugW{%QUylm9Aw3JOi8avmVKp!_I+@#Rk_;O?_h8s!M?BrK z2i`0R=hUPw2-WH|h3J4!s-j1?C$K>Aw&hPJC<9w>mSLyU+Ei*z7z z`ol(^mjw-ew-yh>F6ew4#2KrH!^)CAbihGVkl~%8%}qgq=Jx{b^RhDZ>N?9E*(wE# zLbsq&aV2femxG|mIcPY-9?~04K;m;IG~1rCcunHrO#+cdS(kd-SS|0!6s0> zz6;DO2f*S6ZRqN?5w|*3gO2e$xOG7aMhuX{oHLZRe;p;jK}Dc4(-q5i@VKCllWAdu zDu3zhJ|M2VixzG*<&OJQ!W@q!aG~irmm-*hx*dZcbMsy5_Rx>MTVo8|)pOJ;H41`e zeB&(4p3-ret5Ht7U69!hIF2}T?LNx{M^_ESoOe^W$b09xGa5U%@jBBv$NG&pyJ{WU z)Pp;bmJep(fcKebbrfe~>0rSSfkj`A>=^x@dU(16dHFez8 z^NA2$lmL7ET~K;a0vs#R0__J|aQ5icu(tPSZc?w$)Md~UZjrAg7Vb8t2{G?E-sr_x z-|H&ZUgykZ>;$A&Yq4gI7?>&EqUuhkseWbxY~B<@JEuOQMv+svJ=5kv;-zxnK1soN zBQ~xE1XO9@pCi<_!jP(g=HO-usT5czg@i&)&l+u8$DT5j$AT;!(SF1<0Fk zM9~{+NE23@`{owH{E^BQK_7Ck@^dU*`7Hy)?v`P0eJNeP*QfDWM+NQ`+XeS8EWmN{ z8k}?W2L7k3PUtU!{NaYvxJ^atVUQ7fGxB5887ZNWXn1Y3Uv+=@)Xxi>x zkDvY5@#B`;;-mI#ba)y8vtQ@Ju^G|ewxJi=oK0>NXwHM=<_K=DWi|wTUr%GGDefGx z73kRyT<)f&?RSXteU*VEn`Zv|ZBy~bn*uNuv!MHDZUpliX%JHDLznl7<>#n3!mf;B%$A&F z@y>KUx{fix=&Ih>?iNbB7U*C^Ock7ds)X8xQ^Cs|AS7cq_Koqv{fe>}HbM+HN^9Y= z&pQwvq;tg&9Z}9~Gl)(zfmQ2=LELmntS^hBErOXCxHyM9?v;+`rlmvw1rhjd%|3k0 zW(fVA0V>|v$91`cz=gw=up)U6n!G5&t#<&DhD+h7H)HYE^fE3_ULPC|_|TX^8)0D9 zdT3A&f}4HR`KRkjxLJF)E^P z^`-jrGX?U~iqU>zB`oIqas`SS@OEB4tZQ<>7AG;-@oEPO_Qjyv`lD1_W&@IHMdX>~ znzxHc^F>v*;gsqud_6M?np0Y6^Y~P{ad9lHT~kHhC>V1S;`2eX@j7k3UnJNQ)C-qb zZG;n2dAMED9Jd_&PNl3KQOAQzk*BW9xA?LKB0Q~Op3y}5UT!0}ed72&4;{I_j}jo1N4qYK=tDXc)Z7T4bK|V}QIY>(m zo;>(%)*H^{krUMkp2ux)S_Thp0hB})aZ&rM@p*AH=D(ef)=Bm#d-jUpT+1b{O=}la z_1XcFifcH5Nf}CQTnNRjdUT@PX8QcxK3b%hgFBmx@T`pt-nAaXWwx)vOQ+nq*j^6! z$9F!wtjY&PyL@{7jut3Q-3EF=(r}^07J47pfKlStxN?3xcN8-rOZEl*lpTfZ-oK?K zbqc6FCl~jYWa0PW;2;2L*zf?roFSGFV(whvzo2Akw)-w_+YVNZr2Icf_Ytt-L3 zdn54Ts7`LEKcesY&$KLX6m}{K(9UE4elHr1rFjRajugS9tq1V=tEG_tb`$>(l~{N! zTYv`2IymT<50r{ELqeJ+-FmGbJNh*V-A2g zCb+!69S@0oC^EtH z=}>Py67ENpauz9jxr_x#+@tFpr*FXr-qLjbbC)oD@TnOKrzkZ>-{eT!$Y|=ZPM?a# zC%{bW6I9eh8^>Lc!@L1JtkYKlnU*ArWD^~d5|s-)9anDaf;z6jU>@)vc2W5t0mg`J zz-_%7Xh?%JUhV_r#*(M}q<&I3UN;#6^iT6o9oq>vYhQA!>|^mr*#J=8V+Si|c5(iv zbJ1NfQZTx!0&Vjv@#s4VRB{`R9o{=Ze3K5{>z2(;ez6?XKIC#|WK`h1ts|-xPlQWK zA2?~LEnLeJGjuCdg5fq6bkggya9BhOFYC&~@E!Z;yP1VhueyzYJl`1(ELsf8)#W&) zxQ+XITU@Yv$VG16oC<-bf(kW$;{(Hzr@&GJXIP|S20sSa!fXCA-23o86}g!P%ZJZG zz5L~vyjvV2h0g(wVaEJ|atH3q`k`PMlLD7U*;u@6P6dmimEe+Bj9G89p>n`}x_N{R zx6mpArKaj*$>fdH{)Z#D@2Nrc#5(SQQUVP8VT9`s6@#1EbivZWj<{#YeX8tT20La2 zg7tGnbi5RgUoCQwDNcnEpL*k@XAwZzEF5&_3f&xhjJk=;#n}csFvDOw*ohtIo~OFQ zr<5J=yvzf1e=sh5nht0$-U2f72n^i)f%6ZlfWmWA`QxIrky|?n@}sJ`3@cN#yI=u# z4!vw#F}Vf~tqA4wRxZVRMs~2H*c~&F(Z$AvsCdAZu9#;jFnTx|`$7R;y5I+@3bkMz zR0jD@iYVT<1U~$c0b2ZOa8%kZe4i^om0|H%J=6-8HHM3-g8|e zH_|@iYVgy3XPg06pm};28V`4e-OA@7QdI{7qaSgLbawHp-pU{`ui~`I4{%}PCa5yE zKPHg{(06biH#qbi4i5gaI4TJIgjH$6)di^49aB!XA{oMYXR(d`tq>qJ3DOp%1 zor#}chQgA*OknUpYXmA8s0IqG23nr!;y@opUb-~{f6dMcahOYZVQ z$t~q1mMnUOiuX%}3v=Qcwe|Pmz;eX@GlB$J z^VkU$ioFuc1q~X<1sl>@X)SXnw{sVe7tdnYi0Ljk{+bqGleP+(i z*&YIK2VWwaXHHQ&1qbxgXV2BQ;f&Fzu`X{a99o+Mva}QDOyUuV(t$+HZW^7l_ACyH zT!rQSu6RamGnJU6g9?xPk@(ONY_0!WNDR0Nk7BQ2-@B%GuWt^G%I(keZa=}`ed^o` z-Eo*Jaroin#_$TmFRd=*z4B%xcg47;CGfuX~b(Qd{Uh{;(cd}8gOp^QSMWRJdqe%0v?O!aI*_1;)>5|f`qRe21Oo130W<^e^)I{ zymnGxQKCSGMDFL}WuH*C<{B4&xR_oTs)U@6siA*ez;&7eXPVgRWjYqY2VDp`a{A)LcQuTetg7F=a z^ibpweAzz;Z{{R`gkvPa+6uTu(y>o^1uA_H$IaWi1aHo2(*bK;K)s}yA9>?6UoGnr zH~)}3{zyuq{eDEE!{$V!+4HgV+YVZ*840OFrsBw|eOy#k4JzB)Vg3HYT&|leo`$c2 zF1<`tDqIAtWhF}M-{#&+EQCoFxw!IsKIls1V8P%z=zBU6tIY!FmNH=s<4O~^q_`N* zX7oYjL>=5UU-&LBWyx3e2*S(j{LpH87B}CrhErHv0g_AtF6tC>&2HoItxPHOix@=1 zW}Xo=#%zG$pC>@mwkWRcC84YA4q@1#2%NaA5x>`(!MnOzE^wY0c`tWdpkMotuDzv* zHH(`$t3nYNbS~69GS3$8Y7EB3Dzw^_RVr;emaN;7OltmE ziyMoK*~~S&;KrahfyEZag7We^}5OApji}YuGM2thZ{FF(4%DmvCckA>>eaBt|AF5mkmKB@iDA$;cGf!nISvCJ3!xPS#bR- ze2LPW8qyU$hF!j#k92t~vhvHQVm5(zN=mTSl^T%e76*eP6Nq)~ezLo60~`CI8r!<= z;++@3zSQgl(F|FZGP@G@StyZ5aR#JLZUb@OTF9hdtH6;!H~P_UHan0LLRLLYW_#P8 zav{Z6Vbxwyvea+^k$&yM;15OE;d%x=bO^&WQRMKsO^iz~lGdQ1xVc==4Nj58XVB=&y*&g5k_9GWp}aO}kcOxt==5WPGJ+H8hk zny(R8RicLX`p7_Q;sSDh<6D#s+ebaOE3n22HKt1jl6b{iXn#0?v+Ktb1Z_VD61p3R zoTDv&m(L#V{>)))zlkyKy(LN>_cvnuTism(mgkJIdospi43yKFh7dVmmRgds_mfDwXK7 zw-i^$+~VRM_5!;ZGJ=lE?_Bk|6p--vL2I^;!-Dz!@Tur2?yL4TL9dyqC}&rKOSEIa z{Id?28Kj_Lw&cMB?p4q{6Zqxrekf;XL|xm8;8OHX2un(Zb6Os-&3++vl>6huvtw}9 z>?$s|W*b;q%;GL9)zAqbilIh!6lU*%&D4%7`Lu`AysW|TWTUa#l2CSM2d!BjgTWK@ z;N$fOv{>i|Q-m=_fz2SC+}D;SEhgLx*P*c8v=VaV%{i5ws~~q@e|%Rp9!xHqaa*i- z=)I@_k3Y(Wb4tr_W8bucjrR_5n=5DF3av)!X|xq}=WXYF`H3(zI~rVrl5tnK1-GPm zEUw_$kl@)(Fu?d860gJD)JrQkiDWITaXe=+63sw0d<>4584stb;z)dwEGRj=#Q0ne zpPySvkG?I#g=La#c6u`UUO11_EP9bTqbWo&+!Dsh_h$=SWHEmIM!M$3HGC*K7B@Tb zQMy{1%{&rC62X?dH@JW`E96*uL@&~6Wk98eIikCmDckM56>IldF{?9iB=^xU;`MbG z>L%$?U6p8hMm7feH6DkWFAs3hm?+#d=Rc;$To zeKzzu9#RU1@@a-_x_bt(x!whb?Ox%ct1&PnDU!|i|A;QnBjKogEG>BUlH2g)Jv|?w zN}LU4$l=FRShDyFw4i-iu9i4^lW#$ z4O{$2CM#GqihSyK2Wt20k!+7H?%Bg3WMNbT6kYv-rm;n+AdG#-%?W1JGm7Di@>3M? zGbG0+>k;{CO)~lq84_O}jdO166w!OW$UiS%)%yLT3_{-McS*pW!s zIdV46zi^-1748m|0kgsUXal4)rm|D*`C!@Z!JZ7-$?+AHz`I2ScNN^jF_x7eTc}So z0>+X@LlW4LD@r6&DTq~VyTHBb`~-9D;&An}acn`D7Q7Al4x3-iCy!T_qTVb$w5f1o z-})Nk@+roo?Z6ne@orx>x4!{tGWH`kLSMr~4PE@AI+!^fp2;%4?MIzVC3NVo%$^+{ z#2RLrlFiu;B+jdoyExv1N)W@8-;|{@+OgStD0ZrfVke@XufQ}V}qkX|ye&ys;v>uks*Bvkh4Az`z z?7GxNore?vTK_=}PsTO|ovNebFY0jP?M86JUL4{+Pr5}TL^SZy>smC=-i48kLHvi( zHz*ocq3?q@&NqH1w{zkmXnp)xuyw8r#v0||m)SlZ`WJX$CZHAlbG5LU`LJ-5MWCsoMY*W0PrMtc?_$P##WZUgJ@>oH){APkR8 zK?em{Nb_ljeGPsjC=cgrrNGiD8Dy)TX-;sz6m!^Lm>U6yV4gib(jlhe(#d$jShbsdwQj_I<$kT+*#(FKnk^@T6Xiy@X z@luw=MB0%^S#hXZe}Y<^y^pgkt>MgS8|bIiiuEp6z(IL1`}nmC@=j_K$^3gLVwM6g z%QRW0l^D6{vkooqnPACyKCUfzhWnpYb7IM($+!C6tZiZ|?6R7{iZ#A~iunm3L%d;M z>2tmZwPD4X4`B|w4Z9xk+1jOw_~TR`_HFA{=zm>~JRGVc^gByHU6748K7Iqu-Jf84 zPA)TA^O+m|$e#_aJ;2FNxCA@SIFNCg8l?7R8;z__SvhXSu(ak}l?P}z1!vj3u+J`kQY=e6?_XLN`mH6?}n;_tl8jhX% zgNE@aX#8jfy)W|Yi{ClSzpw^Q=(XbVeVK6Q>MeNIlz>*FTrm5z0eQMQ2bz7;aJjtz z1K#b%u(g^41Axem0&(*O;=>f^}qY?L-o|Es)CyiKgNr#&A0;k4?98!v2S^ zVu14%e4C}lX4yrNK{k6x>2o=(`!;~RUd4mFTs?Nj?hKZEmSt-mjYdabe~j~c4$D5C zCUzDdF|1^ZAWkusdph?TO4Tc{cfO+d{!Ao26CA-+_Y=m47pswCNWcpQ-zf8`hv`?x z(?6Qc_@Aqjaq~<~{vw+g6uS}4xtN@QLJ==8Y)FCH$(C^2rUC0Go~DVPvY>R>d3qEI zxCsM7@lE_{u-y7ykoVS$mY-u>)z0VKf;Knc31f~AzDwbBT@~zfh@z94H)5x>7w2|| za^Yo;uzBN7RBw{u?6*CkD>Bt-^OsUs+$R||Kf2+x&N#q_f7f*)%>j5MQ=@1o>9NmAqUA!-VlBkE{m* zeo`dK4~^oAqF1mpPaol?!M3a+R*q~+c+IVTn1j*l77*W8b*S8DIdQwENOW&rLYb)e z#-`3J_SAa{p7NgtZp9Dj{x{NK`XK`|L|lp3M=LZ}Q4`oLaR8TQ8zxbHk*nEx83e1A zF_pM#ICL+JeNx{+bare3EIq_+IQRqJ4_?aF_A`dHmwmY*ug0>%5#PX5!-HA8n?#=6 z6J_#td*SZV5p;}BB2IYkf}YdF2|2Z&#YSaA?O8Ear#ptM53az>t%=0HfI1gDymjno^ z6xiGfz(2;v;)d)yWM705@xSiR_}6v$BR7f>ea9N6H)#l4x|OgOQ)S>tUK+R@=^(jF z29m^WCMi z5zm6u`jesMW0=8`Eo9xCiCCLeOT6=CN#BFQ^`g&LES}U3Y0QdAM^r<7rhsKirIM^S zp9P-^hZCibL&&C;^|Vtj1*b_&18?sVoO&e%)=k>Uu9dYwV?aE1=x0K%k2Bq}sZIq|a6N+MVGOH}o1?p{fE&Cj zla)=a;_MPqxN*~sFgURfX)E%kuC@d4;Lguj*}ejXuf7M%){bRQZn?}VQ+V4kkGs<#PzWwdmxP4H$K@wG8d$>ruQAx$><7>eJ9RZ!e_Jj ztJDcTP_#@j_P{f*vT@Gf{$$L0!tPoaFm2uGoWtWJ&eA~#SLi7gFgBcX~bKuVbD!M zuL~T8iCv}cQVJj@enBvF_(ojUWsB1a1GudX5s-f_5*#cqQ-Sn$l%4Shm(qU_jMBS9 zR|)rK&bKAt`(ekq>n$n#uwX#V(nM@M^pvK1Zl(J-i(}9vy@TVYz2_RN+Ub+639znN z6Q(KawQrN+t_jK=R09)~FkewUZvg z>E=&V#oG(7$bY249!2~_H9m>G=|y;pW~0??Q+9g(b82cakW>#2hotvrEYa5&AI;f| zN(rhY@JlbElctRQ3eRK9^&j}6(2c0I?E;DTBE<*uBq3qqKCa(WC zd8#-vi8CKj4nyDXW)4pyapjtcZ0Iv7vhs--G3)ykUVc_3rw8cMDfy~IzSEFwiao(T zIK9GEXU4N5ipk`eUW>ARpD z(|CC#(5Z;b+BJlQ2Ij(q*E5KmVJ$Q6n~$I`t9xKxH z0M{IP9`p(ju5~=5SmlaEZ4ynn3*5;=?YU&fYjOOT?+6;H zrg&6hF(%IZ1lE_Aqk+S4qBy0Nshag6Ro)}Htpi4*XxUf3?d=cfcWEyQ0_DjE&C6KV zbO%Ncn$EsY&*QeKM*`g9|DyQ`SR%k6-{+498t zuoAN@8BE>^-_Kmbj-$3-D!buwfs?3^w6r2YY?^EYmD%P)Mjo2X9=?(XqxXxMl9U-s zTe60oP!_;iO%ux*xOTW9s;8*S0{HVV6nc2lJ{ zCQ$sMgL^Vrj(#+X!zu+e&LF&!<82S4?_1MAM63wEN8N|C=qz}&wFKXGDWbJk9k=V@ zdYZJY18y#Si_c1rp~7cf+&?dsIN3|#j{DBI(kdBq;u1KmkA?7If<4LY7eo)-9>Oj- zRb%Ia738?TD&0`x#j1)-vBT^Lo#VEOXspbIyJHDA=duOsJLxFOtn?zo=Cp&z!$&wF zCYpZm9>_B8UEx<8RK?L>tEptkLdB!HhAD+y5Yenc)EWo)`-s`r#`oGrzFZz zAa@wb#>|7Xp#`{uII|+rVI*{H9j=Ix6uukohSjv?B28I_sxijM;lDo z*@lxIR)XW56)a(?JUreTPhK|qAZV(?W~oao=F}iEZ0&ov!AqxZeX3~rq9V3;?PlDz z;sfxU?@)GBkEF`2XVLTCgZPx!;5x$_mtIsRo=)XV#%3orE_)3I@eHNHSCNhnYniQR zAxzj|Pr@DyVO8Z7MDN*XwrAor)<>@wn{`BtX%1Jlyx%;6J-hXR+V$H&jJG+ksHB77 z79!3rM5(j+H^#DA=1W+|>u}4%5lfjlFA={SG$U<4^w{%tudwmE9e#J;NBu+d=$4sR zamg4B%jBbL&>&s7u5~4IHU^Q{`wvm3ACt+?T~$k!GAi+wS**p^%R|U##q*T!VE_q5 zN8on)O+1m9&RMA0px9D7I8d_(28Dm26L;3YCE=dU(oxmm5g`s=s`b$PVK(j@y-DED ztYGNdIJoAjA-F3%KryPWo{Qg*2BI~5*mf_T+DtJ-Esr2den?vXs;jD0kR7sHsW zRH}3#5hT5*LwVtGd~YgBwHvE(j_(+-X$wL@^Bw%$_b@l*S_!PUphDR212`gZI|j}S zq65agZj6k)Ca^zY8@K5RziSxo5Q>|$V(5r4KFqZ| zj~CtYadO=c{NdtBTyOLuoofp5+=zqtDk2?sNF=~m(O$F}#F&w~Gb1^OvmZDS^XV#N z`<+z0+nR{uOe9g%el`wYQ`YELr^bpSLg21-J$4^DY}HgD;|5%UQ-ki{8RwnY=f?uJ zRr@$5xq0EbhxOpX7?seRn8vvK6}GgaUWP4SAdDXVuc#EE-XGUp6aOwYC?4?NbP z&blm)H-90Sp>GCHM;UON_9(Guv#K$PGn z=;>vw!Rr*psB|%9Uo}V)#1NS*Ex2BKhjyfzkU+2LBz@)sjyGL}otRUMLnI}d4xYIN z@l(Ue5YXb%D=M(V+L_!coJ>AjU!ke*dqYCCCYyWv6uU=S;CxCm5gjv*#lLyM-`mH7 zcvmEYE87ZAkxR*pb#s`CQ57xv_zrS)@xQE3)>e<9==Hflcg#!cI$OcOf!>7 zbA4!`j5@j1wG|7NtK#l?fh=IjMzVeEeK_JDjBovhk_VILvw%A;*t%dP&5?`1{%_?- zspoiR<9P|PAF7hUSz&zXtu&tw&?0wQx^9NRlkowXPZC;eKY zu)p3dpc*!;@ymUT6TOPrHY-_0=@`rQP2-rs-SdLoDmmQMGg5373B{+veV-EpOgIs< zg%H{G71w?rW|?XHDHWD<{P61pKkEO+Z9OPnL${0 zb0CJ~8sOQRN6;y70^F243!iJYcz&mx`+*sLHK&OP_USAE^xLlPx6EqcX z#vHcrQWL|e&(#G{%kgVQzWR&hT+P^uHO_6=V3i>uOm#tm! z!f_l)OW6uJm(1{w>apZR_zDto@)9~8c4r6jZn2R$cbIqF8glzZCn&7qkp&9F$nUkAO4R+3F$IkR>N{Yy1Qfs%69bO!f3wUAvdD;l#t+Jk&KXxJKhD!0TifJ(C zXVOiP8q*lFPas3Ds*}$XJ&_sf3apl0fH&=WehB39q4S^mP8WYxf65Oq8PGQBg&q$vYH zBQJ(snXPX5X|8CK$>lg=9P^y*c_U6H_9kra;$>vS;}&vzXd~6+-DMw(R4gwShB8iK z0{Q5Bn^P@pK=}*ETv;n|)H}(Q&$t8l>^bwWQX&e{er)a74mh$tiv;WrWXsCySXb^P za$t|}UGZuNsj6R#v#o5Ywc0o~sjn7UQa)7pEHaM`=VDm;jv7+(y%klAL&($PXXr}P zUTkkb83rhbkXz#O1uw1)V*6e!V}ploB;KaEIACTG`Iz(;as#}v+2Vx7m}C0H$5Ikj z_1(inmb$S~{lZAgwphrKb|k&G9EXbZQyAl^fmebgu*(>OhH+DS2 zKi){1Y7>cQFH`0#Y*XQr2Ef2Nnl`hQ5sM_4NT-vmmXT!O0)3)#%a(j{FlBx2jKy@L zO!_6lo~ahRW4+J%aM}~3$rGgvGFo_?J?P0g(m0W$FU7CY$}>7Fc2EYhUObR}c2pzc zQN2%@O z2UO;*7(UM7;QWF&7PoTjK>n#cj<+nu;$dg0pduRPcuj?dw#69KYX(;7r(#WQG*>&q z6^34k0?AVoaZ2zZj4i2vX`iEn{z(d*9j4-dbXm44Ku=&j(gNO1OD9unLQpoM2@4W* z@M2;VJ{akTB@+Uny<{prT0RPIi+#ifqnYIT*hH9fbtG{Lo6NPC#Bmc);)F<(#l#wx5=&u6M?Z4rd;zSDuLGIv zCva|T38_84QFyNV0ZP`7Y?^-I4AZIb62=<)5w!!}cR^&GGZt zzw9L&HL94E?I|GBl8%FJ*%dJBI0cq(lu4VcFX0?!;oa-0>|6gfw)*h|7S<3;x@@m- zK|l0JxKshSejY%UCafZZ9aA~E<@W5!7Kx@^wlZj#(m?v!P9}6pUZZWm3(jcp0Cau1 zh%9<~hFU5j+xqGe%l?>&erx+%j(bo<^!m;q$K5ZZxVebn=!imqlbKL~LB zM4G1Qo+Cpr$dS+udX2E>=tX*>LKIT055ei+GBo*A07~C=F|7W*a6fE1oQurFA%>4& zB^6OHa|>J`0wE1W<)OtYO~@xF3+Tq zS;sh|AFcdaQ_7z?Qi>aNdCk?rOR&sN59No5pslVNZ9Zp1x8xY$rxbU( z<8TJ&pk0R-GW*kgo$0_&NENh;`k{5@W|%lN6%#rtaYfM|^tnI+gBLA;WpdisE;66y z@TP$1Wa0UsC$r(o=f1FX-U?jZCI)4lZ5FAIoZ#6NEfjix7CPAi*6~`ny=R?B%jDhA zd_9xPKHM8781i8BPI-3qlmx3R+lIHpDq+>F>Ga^@1thLj3D(Mmk@j6J;QeR{jvxJo zE!Wjy>XynxrC=Ep`5c39F;`(|r8eEvl1#qIOeF0lV>ywR%1vuxx3Q+vo5=A8i}{9X zeaK3$<&avT3?ff@lR*m~!Ig~+U5_a>jg(7bQ4w3n-LY#x?ywU~2|Lb79*^SIcl09n z#&^NMiL$u+RI*OjQ$*M8G>B(rk{FfeIHAm) zRNVPM7xLybtsGH7RFmIwj}8oJ8mlnEa?){G*7k80;rIsZw!$YmPF|a>^2lSm5+A|) zC9Y(3x)oV(y|PqJ@~CLRyfn%Z<)VX}lR z6HDDlCCfs|Gq0n}s{eJ`XSY5{lae7)>5U{n=wEb$c7qN(jq~T9g%u*v1PtZbKm!<%xLDbUUp(eGnE#ZiUmhg=E}B&U&^g8-FJSwF@&?IW8eO zy4&$-+g`bD%BKkB$3u3*-HcGwDyO$it)+Y}yoQl5iEs+dT?& zx#=WQt7c8O8X0zI=t(?cwTa1}`2X5_@2D!8W?h_MAW9IBAWBdH5hW-hyQ@J|6a)oD z!9-B90tQ4yRC3ND0uoh_pd=&gsYWnk4wwaVLQzo6;WzK+`~J?l-(Bb4yY63St#fCu zneLhCnLSghrl+T>o~OFujo2mjAt{N@;GV(jNK44Il!MXN57Fkr=UnmKC|oy4oCS#Y zaawBpr)2j4s{xPlpmlBvl&6ki>l{M(vEM?>NGJw5x`#AQH^k3D4JNq&V4sm2U)l`dlYF{B2Q^zI|N+4$9*b@2EoFk7%rtx8E?-xIeaP@Ov+~W z9D>-BC9~-UpAM1|qzaL!O{eUYXSor^bn@pZ)aT4G{N-27HVO8y_>ZUPS#02B50!&@ zpo8E`!z}OW=T|GQ4Cb4e1}^fexZG-KTCU&1E%>KXlh9?+gzxQded^q^UNeF zVc|3s-%p+eh-jci#~8%Ue)<>H$QyP4ai3cAkLi7u;8fozauaO8>S51xza6Z#nM&_tBT-v`E4>59xz#i(YUi4%)Cq(gH00smWa83}{H*0M1Zb z1qF`N>2J|-OykBu7`NgeZzDHj51l`u=(-cQfsP_+9n+a;m^=;50V;1F#k>USRQ*gC z{a{~$$$3BV$i>SjAvTR{I3Ui7x0O<%qAYETQD;8}Fob|3G<)6=L`4tc`cn(Ncwcjd z{7;%xyFw#OC(J>Z#mOF!3wG|F@cnhPo z)Y0zsWgKmrN`8!~ME?UrVIFZq`A^$%T=#yQ$YTdT3zvYhW*X=JLK8J?thw4ddm*F6 z33Y$0=Z4qRLWXn|o*r3+Qqs%e;=wg|>F8!`6Q6@H{u${gp3j}%Pw?c_@4|AMd`?49 z2(I#3Lc^#CB=t{-xz-@u{P8LI`KBJ{xa~z}trW=nv=qX2+F{UR3$i--8n?8^4;l&^ zxH(eW;kb_}**AqQXP@I>%{+BM!tr#$HQBS^T$+tpKcqmtJ+fI@wi;Kh zt|B{BV_|~t-ezDb^xO9fn4zQv$A1ooEbpmo;uv2Zf7r!|jU6L2SulidR@pVBOydpI z-#>-9(IaU~Du=due0IwEgtNN0EtMX4zc@MVq{3+nQtd6%XzoE|}6 zPF#x%Z^yE%v2pNt)F67yNtvbC@Hl9VW+pN3IHgTrQRLSm8hzV_jR?1A6Q3tTqCpD1 z;;hGv)-^!nk7CvkUP^DS9K+cZyVADkG*+S+%^uu63Z3D0bm|f})@hyuFWC}S;}}I} z_^Q*HLx4J(rLbp17vWWn!@|-WE7~^xGE>hJgPA2gJSJ%^b#)m}D+{V<`@%Ff=9L%= z`WXV+x_U6T(~muGOcNxPtFy-!mQbbeMxo#FD(VybkU?~=P-mMWH^*i#YU+eT;Er9O z`}!H^4N;^gwuCOwCMC4ravxg^4}uH)cjls$A9|?@2eJp zDLcnb1s$M+W0aWsDbk`6GsNoqlmLOZ`(D_&b0E%dpiJ_hKD~1;gbDjs(8kJ<%)L^h zMc5cm)9z_v%X-)5e%BJZgv(-1j>=H|u!AdAZiRz`>%pz@HM?!u z8JDcer^zl7O!fRBHqt_gB`KtH%L9i{+q`m86CuIGW_8e-xMKYMZ5fC?D@T!}cy`Bo zA_@Y}f|80WogwuI9Ya^Z%r8f&%{faZ)s{=fEl{8>U`Xe;_ckk5TOB*%2; z?*hAJWwgn$maWT?p%>N}@MEHQ{K4C+y=tJU z(UMLLt3W?z%F44xP!pqNT&{c^E-u>(I3b9>dGG<}xB9a8FYM|2;=_Ux|0uk+<0!nJ zrh^9`+2dGE13J>92%Mcg*j%STrW`Fo7goO}S^{h8ShN6-RUO7>AInhd%zl_@VSo~c z2eCLGX%;51#@zSQP-Al?Ju=e{`xBCI*Ao}~wpRn+{L02+u>oNGeIPr2DH2;1=fU>q zW*FyopL>_%oc11+m_G7TyzImxylL^ zU)aGV4IQkbCrQSMT` zM~y=5A2nDQF$mL+sA7+5A?K*Q2q&j4#g?3I&i%(RVTblDVP1_mm#(rMa=hPjDQ%@7 zwLKLcs@9S5$76_z;V+I`GaKKZC=qO&I0IuAr||c?0$jsy!KKBmWa-8nu(xeN{R~qW z_1z6~6Sm;@bJdXV7mtr4?WltNT>4jkR~)qn?uhEKmg;P5b}hl-CKtG8!ce;Nwmd$V zWCSm7x* z32hfwW8%-2GADiuHtr(lOarE+d|qkp_2XZ+C<~tTI19!`|G){GJ2>bP?OKP%z7s8Cx5nq<=-s=TKo`Qvs-ANa0eT` zSr2p+R&t$bpJDB*r#Qs<5-6PChgY_uKqXCxx658rm;F*Lz7`_X%(e-(w^TA0|4Hz0 zVkKR1LIq!M83#|*2Qf#U%i_hL^~_sqEB&3)g6T_4S`2PA(EeG8)KDuOYBzV0gKswUrRS!&0uPp=Yjoxi=GR&!dR1P zd~bA>T^}X^_g#|7i9?=D;@MAn21Glw8s57mo}{qwwuY*qo1>wujpIy(DfxO zU0=#(Ms`42{xoV@BuyRdI(hDfXcE_$NwJDC^RIKT-8dBHp6kmP0hA9Pu zpMpuRqy<-ZrBOeZZA`vu94q+R2o9c4&{@9-91rWz@Duj1@+Boo5gOnzC6qQ5EoB$p zFJwnvkEWv)Oj#Bm<9Fw0Fpc>69Me{~!O#t&LZ3AwxkK(TY`sqm8~T1QZOZ&a1&(;?Q3r0&e0Ssac9Xz6QiD;xr~Eh2j>QDsa@y0>j&;+^nVt#Nx*? z+*B?hC>zm5WF~c!eXGjRYpx|X%BB=cqz`}yq&9C(*avG~m0|AOkzn^~5+3@!8@1G3 z1*I!_9F@x$!78iM+#s*L@N0n|wzThpFE|#%-<86F(udsgm78GV_yL^3eRp`Y{2{qJ ztz8(cd67GRq?QW{a>T^DJB4zaZj+a_Q_++=k4o2Hp!xLzfqv~6kUv)ogUjUD;Mw;{ z-;NS|{nQL<`X6yiPCe&Vv`fK;ksC3v-G-$?ObGHs2|q zyAv>*8YB&3b*}leZ{T^@w6GB0>?;IK^)g(YHk8%>&}ZSdOquyDD|-7$D*L=6nqCih zg5MezLbG=~v{#;o?5~u$+|Xdd<9+aerwiR(zJ{F`qfF1m4q=ix)OKAV%^TS+;cd^VJMm7j+llPj4QkC)o{LWkv#$fvt~GzDLlNVXI|@1O@a&Zc*) zZ({sc3wlPRo~>DHM@P?jPfi&wr@gWV@s;PG7Qu&hs`Bm;RPM-TkCyh++s-T5Xr6bW zcK&DB=NSdluE-LzRAgVeqcOXx7dGG1W5(OrGhclTVR=aulNNbebd=m#-5m41V{E`|AHH6>JftKdvwIk(Nv8Mm?RENM*_jF}_H za>_NSPyALYe?tii69>bb+)_B7a0K_C*~}g93uVvj_XsXme&aF=F4M3=En;$N3kF&Y zq)+8WpyU&O95OK*C3+XL^KlpOvCCwLUL<1m-s1}z?Cr;mTgKp<13JPXmzH9rYz=qZ zrHbs*-;Nt>4wKC8F7Qum#CYWr40Vgdbp?Zo%!o-?^W+Anrz?isHq1M6k+{~#@xi36FS&~{b zABPhL`r;!6v7uF5`K03{S9}(CHrxXa7U;vl&0#3{b`rQOC<5E#eS+v(6s(-10wG#M z@yYcf?#EJ|$ELY~)8p##QK)(I_zoZJOVZNv#!l>-QnF-du(c>yJ^N#AqsWR+;Taci8k*i~X*!!e_xf z`10aMywWI1=M^ik*WG#4?@A<<`8|vo>Bi8n4^!AU-B9e;)5S5tmoa;g2z^uE%Eryx zNZ(H|he_^T_+nrgwSBFFK}Vd}j05w@EM*%!zF(R~>a1p;#WvE?suT)PGUy$c2(m7GZ}F2HpI=Y??9t@C2P|Xr~XA-utaq+ zZ4o5m@e9_l@JlMAOY#J3!hjtx^rMgN#;~amV(GaBZ@48%<+P8fF+uZ0YFvMp$+|Zq z8${U8pb~mjzk&@8@}ZwR24Qh!9GRgokd$Z4rIU(wvv*c9tm6Iz_EGL6m6x+&N3Uqm zGYK|at49t?8Py4m);p-+<_$JwPzkI`QDz%1AEvDl_b~CBHFY^Mhy7^bn8o!1dYZ1L z5lb#G7l~3zAK%A;62s|=mi_QcXCIk2Xdt`wx|(fmpH3@4`Gh{8C@vVg~ zyjO7{@0WC;l$9zBH76`3wHHHVQn3EhS>YbR0@~iS1Kve&L_*CH#YTU|e7*ZHGu;nk zBv!Iz^4~#vnl&9cZwT!ePSHccnflv}!-#f8w(`3>J}z2>K6B&Q$N67j#peVXe{KMq zsV7H;u{u=tLo*(`pvp9Ai*d+iMeNHrW2wvT!EYaZ>h$(LM*6IV>`FOm`rHA7X6m4` z^Hn@_ebp3jSc(%bPldI{X0+4J17#++!h0hn8gl;!3XcMm{i zBIA4(`^;D z>aF&${AMQ_O&`zREVk!40~Og}p7+Y*;Ys0qn?@?vegyR&e?kM<`N9pHC>ANK=e$m* zqV}uTq%vqFh`$WM+NGzsF3B4tV-U}UXuA{MA6x}5OtYc>eG~+ZkcHTyvEbV8hKdW5 zxsu_Au-3o=wcm*fu8T=Pw@MoHI$C0_e1B7j_a`zkp67yjdYZH6c?fSlQs4p`55Vc~ z7fAC;4OB=7gZ{t-d_5@6iOu~Bq&7yoVJR)`CuO{s$^VV0YsG3sOw zW<1Tox333N=YtV!{B1S5!TKbfYIhRT<B`pZ~6>qa%B2p)2b8j6Rp`!lWSrU~h+ZbArEU-J&{VJRK@bPg*Vp30iFlVE|`6&h5tfgRnc zfNxsk*_p>bNJWGMR;bI<&u^31sVBwE?o%4f`goV-OGKi&Q6#9njc2QuNU>9LigZWv zUh0@@z{YEz!0TsaX-sqq{hT$qzKx%PG9w_gw`{_xpxx+_n*2KX=^x zUV%Oq?iTE8oy&f7in67lmE63kKZWvqjH+GFAo^r*D@-~W2ck}%^h&8bYY?90^lQ|Z z)~iuC^RN{TSlS4)A`Izwt*hkZrDB}E*p%Ml@t`K&8G=0BpBV8j7;Qa!$<*KXV9#z_ zsxV~`yS#BbH*}K*4NW+}62;G;?w#kj{r-5gjb6n`KUL+i3yO4HurpI!Jy)3GVMT{H ztYFDGdBDBDh%oykzEM|1)cZs%gyZOhix8*kD_3yi-v%*}xstRsdMvw_)QV~w*C2}uq-`BT zF-Kd1&2Ah;m)|mjj;=P+&{oVf`Ssz%ozAE@AcMPEmqd>g5bTu75suvRf#jU>Bzu0= zVzSO?oZ&wmRFB`_e(9)i>rKxIXY-t0ALi;crx9Ip!DcraiN}C<2BK=i67=uqIkP$$ zahB^5W{VHOaT~NiWMiyg-`g5Iw=_w(nYZ$p_d9UGam zHB`Kafc#adJZC`$z8{vv3DcCDMe6TzQCr5sw6BUdOMNY*78iqW-WWW(Pf=i5sSSqF z2hjddw;+4V3C?sP;4&3aEXn#VA%kj`>7aLVbZh0m5CAUwwapiE@T;fJkzVH~-R2{nEt~N9J zwv+ekmf*PLUQD(32eAiJnW^zmT6T9W4YiVGUXM4^aZ^K>yAXc83(1*AcX~VVoSMAnK?Pb@->(fZ-F?8pGOvWIxX+`O2*7K^6INCT;5sV>do1fz6w0HVpRC2RUs}8M=^a$xxOqpTxc!cYxpa7HW8L z63g?RkB>$_W~WT~am&$+qZjj>=q1xoR$;b^nRG{xq9c_ws418{@G(OD(=DtcWB^_9 z%m9~bah6Zl7GY1$23Bug0{FCo4$gSOY36#s@iA<)Lg%Ri6kYH>pDTqUA(pe%nWED` zE#Mq-TM&Ns0KDtG53{vOS(%zKen?-)MkKl6iOU;lsM=*P7skD)2R&-fs2AUl)#1}@*)Oy6`!)BI3drX5lZDdLx5>(+91X8$*#+~poz*(HiM zuZ<&xU3016#a7xdl!uBigy& zhRccL^iEviu1Bta%Hm^l4}p8*CGh6C&rZ%*g*)a{fx+*O#Hd{odPM3;>qP#WX+Sm! z-I5JTLTB(BH3Dswb8x%{U?-1n+L;FeE@rL+5K%bt6?u(PFrD8GqD`SzUYwjVQzLO|76m zZwvi2eIJgVcbNOuJrxajF2eX{iDa6gF}K*$9gA{3Ff^qDj3<=Roo^CxjqxD567OJ9 zfjm>#8Hkf=bMa331^8T&3Yy0qXcMoeX3F(gTO|({r_5q+>Td8nC!52P1wXnsf7V;G-I*~GwE5$HSlo!eR$N@ zf;T(M*{$s=bZAsEJ(jwh-4t*bIdeR#maL>i5MOOwn3a(WqN6U2>Nk-XZkdc8i*7=Ea0?BXIfOm!-2xxL zhBXcQzmW2;-|bl{Bt14zpP<;``&UEXV2_RIt<>$jtKGp=)zi;W=f z0go*(xX67q$Y)dcjG-bONf?k|3N|;jneXuox-s@4S3f%$4_{89EwxDkf74m4`}{Ey zwWElPH@bkOBYjXapn$%6r_9>26EQM#CqVoy@=|*=)Ap2siC#}hVuY^X%d)+9=r`grsA0UUd$nrH{S1f_%fFf}*J@|^K*vT{isPTpbz2ipR08OCC_ zdp=5iYeX+EWB9#%9!^@b8V?L~ho@H(vCm5phg%ceS&{(0E(6G()!m%R`Wc|_Jd8X@ zU4;#4v!K1N6z7zdgR}fg?orq@cw4_1N_)41)rTTZ*~OaN{a}M%?Lxub%?zVwRAAMx zbQl_w0^QeN6F294lG&<)y7Ix`yE&3P5Y54|C8=b3{8$W`XTraiTyeCz39-(b!gE?V zpwZN++=($flwJtt6n3u{Y>Pj@-8@k)@SS0c-;WPOb-_VYy>}3NYahbx z;Wt2IYX%wgZ5|hMW*qdazRsO&ED=07TnKt9hq-O*hJu>mD|lgTMAr^@#rY@8(cLw> zaD*|3q47Sfc&8pbIABhqA)aze^P%wEP}&vz5*0J9a_^&WW95`8G+J{4hhE=+`8!TS zc-Kh!GDM1=dbE%p>yTgtW|KIl=S!LD_+dD7^dy+9ZG#41GU3v67dqT*8EyNaOm9z` z&oscD%bm86ZAeOln*&{d+o;1Xz3PWmW6k06?5R|A&t=ZDS(EAIKLOvBQOw-D1P?Da zgD(F=c&EP;<~u%tUgIV7W79`sQ1}gXGc$OOc3n1Od>STfk>w&rNV6L47a%*C;|{JK zK&Ss22xZINFx^>JwQdNbYQo+15vMHxt2wB;C|#2 zX+7VK2VW(?0>5;8b$l5;(#F^$oilg73Q#xOs9DSG(Se$4Z8 zrFM%8*b|9Qq%2&Q-G#Rp{85e0c*|qKbT+a}8?9;g#*^sczLbtR-G{=wZ^)CcbGdSt zxYfVKsZYBv>{d`?+ccHwg84kJ(BffqugnPOFlfh`STmx&^9a#XiHF^@AH(4_Lvi_t zE@-_njnye?!u@M@^rf?p;I1>z<>juAV3H%}$&%$ZC*oz@F#2ls zR7kEX=5gYip!VAsxW+jPz0BwFv3Vi5>RLE!9PWo--IeGiZy)MXavUZ#NP~)uDqO#l z3kFH6*xj-HLOXX;ru>3&23^{8xcf_ROFIKar$p%1%)_v7$^(oW!t-C9kb@7>6>QYT z6UhDY1@o448tQ%)%&My`SB;-R#g0wIte8V==c+W!j_Jeg*W{VaJY&#bmPySG9Z~Aj z5%?Na4cd>~nn$-6uwU=%1bm(V}q{?ovix>l~0D!5zf1b&~GAJ=Q9Kgr9VNFlPO3(X%S4a zlA>a(%rLWD1of;^c>C%loUF$C_#GS|OT7htd^|)7O+~o2wnT2@@?-c??i@ae)5P5+ z54mF_XW$Om>tx!dBtcY+3R!bIh%>$FkFNfEQKo$k_I~Ri&qYnSi^p2Xll#lCCV2|f zz4=6R)x02Ma5jz)kwSx$_lWka60YP+0E|Xi?!w7(PVSSC$j*p@wG(V%dQ2(F>Zpeh zVLj~lvJW20DiX2z3t+-_H#9961<{Ky2ps(lP(*4mT95bOMB~~y{ph_gKcxx{9Ty8X z+;u?R9Y=_Zk_kd)Ek=BN#|>Cm0`iilIU|cac-wM^fJ-Jcd|n9OzSIgmwlrg0U4UR< znKUl4x({R7cKGBMh(Ye1oYA!VBr71f+4BDL<{FVr+);}i&|N+l*QE@h%E|)F9MdLv zI3xj2Ysf*NXe(yQ7~!sardVaNiDq@=k&0}8dhe+!T>VNw=B6PoFuFyS%N}MaA!^Va z^pV@$l|43pJ8Ij)AEY;LwjaOmmz~dy?leu5AHM?3u`2m757O?DvpaYlc#D zJ6U#iQv)WNo3hETMo`}sC75*LGipy#pod-_hf6hgAR_j3(~8r#Ih&psxUkZMx0|dX zicmBzoW|5>MNti!k`vH`o-@#OeM@Lg$IQVYX~Ci@&GDWUeftKNE*A zF~ex;ym=8@)|AHcm@5nKG?}xR-Co4l(~kLC+{5;598Fy+$@X?7QzP%$xY7F+iJzW~ zDK}oCf!tFVGAt{TN$K0n4!ds?}gKL2LF>jIWLF%wg*N@!T~aHh-i4NXlm zps)5{!yjG|XcKAub)q(_4>6S;o6N?#1^xxbf9YswNDlenwmEp|G z5FsT_hn^`Nj}zwXK=U0BAz<@KG`}f_)8;FJu*4e_JF9SbvKmepZA_Ii3dq);y|6J? znMM~C!oKXiTP4G_dB(xc$r;e_}um4c5i zmhoedy*MoN7;386V@t_syl)_i=UZKI<}GDG^W`b{>Ff_q`)LMxJbuZ|dQnOIMH|S3 zTU9*ITsj_GoJ#su&Vt&ZBS2o<8ekpt*dd^+RSvL;l zdghu#I-eJ1ZX@7sKSNxumyQK9x8n1pi`)>N7tc2)1Vu80+_yX@U~xw9c-&-A=efe; zbKPOKRTN};u7|vZ<2mC^+d-p=0Z(s2dSZ5S!Pm+$qH8dyh}w}E)9!FR`MmFOY!CVT zwT>JJ$%AY8xmXsl9Y6FJ;s?n>{242UWtw$7_j(WKImeBAp%6n}Fc;Y2aDqehBWF*< zp-Y_;oUjPQyUFtKlOL~acyb;dhfQVecY!|QxdQv%4##6_ByiK>4`Ak~&bGbT19P$} zar(Xc@a@B3wnR0L{(NnS@m`lnk-dvx(fwUCxv8ARO&tIqvf{b;3N5&;J%U}kRzWqZ zZ*%gxWjLmk&$n~hh9-Pk%&c0+gI)PkTsZ13_KJ$JF<*1yvysMmxRdL6Hihi3n9bhx ztz^F!=1>|b2`8s{(e|bRtoxfjEw*Vty11{0xD`7P%OdY-C5|^Voo>km{QH%LYO$thnMLZ}AK5S3xW z%0wu!-OlDnY7>jwx%6~XJWjNoO*_{{G4eqTQuSo$&tYrX$+6$K6O+o=p0TNr!^avP zU;Y(89Z;tZI;PAjT%I2GB~&#!kv(pD!l_S5Voiye!W+t?=*)A4*s*asy)eR)=i%!C z#}-2>Gj%mLf1463_V8irp7b~8&c6!9TyXOTpGu(P-I;~(1t*>9L)*{^)0iyF`f7~l zw>*L@?J?wD=X0*f_9%#mF2Mx)jHsCmrq4$7gQTi5JJ`DyF9gbfq?i=mEyqTme&`&snH(AQ0;38i!MSxG1j9C+M~%JxaIJh598JB2pN0=)wINICu z)4*WM34FgjJ=T^GotY<`tLds)CIwQjlEa zOtN!}@nYU9;bWb2fws{~F59V&JO05OZhSn)RiDkq0)^4&b4UcT=VgHRJ`sq1v;+00 zttFES4#4X0;hgO~z+D0HAQDS0zsHt?+r`cJY0ED3Kf&i2k{gajZ}}MB`6(#=YXF~1 zX%^})HzTDXrv(uqmpF~Xa(sRm5o905FngX0bevbl6MK1_(t~{A5updTJC5Y-e%%5k zi`yi9W*{_{^EsXlHo&JrrQG>O$BRvPF8v00M5#kxcPotK zG4Z4I6N%U&3uy6L0$M2paaLyy8uf!9?bIEZ+qFxOGQ9@n+;ecU$$V;baX7A9lEWR_ z`da85Zjb9-Z(!>?eK5ArLBT6EP~KDwPx;>_i-W@8t_RIa((;Mif&nb-zyLPFb3N6) zq0C;*utxjy6+~-{AALD!B=gZ5OV_NJ*?drcI?8{b?B0W=^hQJwi*R|({j$7=UOetn z$n&jbTr;G$g}_3RU76_YAxyrnj!r$t^E|KV<`Ula3fdf(QKu3oR(C%JxFS9FP%Vbp zuD*gh0uIuzGJX&QZa_dA}Q z6^AKTmf{7O4Y2;)P8MLF4_x>F?5q!^?b9AZ*O-~KY{d?IUuq0r-L9jaB=FnW<{?&E}jLmz>y))d1fZ=Y3JXOPaAm7 z{X_Jz_iwKEX&J6Nox>Gwb3>PRjNAN67K0DuAl08&qc@mtSEe6KXd@TQ<5=@-uglD$a!ELqC z!s+QFczlEy}=SCGnH)LQ`Rpim_o%aOJTLyqbTN32Xer(ygMw<99m;)a~ z`S{gcQ?T2u2Hrf170R^gz-3=PHhtkNa(S#h5K%pd&5j0jk2u`AYX!Vo?TA;m%fj_} z4>%DXKY#Q}n;<$y6OQehqEzV<1Fk9YDhwLB(> z?;Bbh${|v(g&R^Liwowg!qsK_k$XP?MR~vW?d92Ad0ZYoe!CJxWU~ai7t3MspfG%J zMNw$GxL$a#!UpGF^&n7VfUakE(Mdbx$yk$OtN+O%;sAUy@gASFOd1uc9N6{ z>q+sM_r%jNh}-Za8{TW4;IxXD!IWcKpcecEhjUZVuP>Opd|8QXNjOR%RGWrb@VIf+ zY&<;0Sm>pdipy@=;EL!q5SFzXC)*iAd09Rw?dj+9+{}VEm6OqAwGDn79EK`zYu*nIqmuW+0^ANzXGA2*K(PlDv$-c9m(jy+n^5dxrtp$h z7|{#Z3T5^tY}b!b_(t;xUPyMO)p?G>&d)hCz<2=XJ!Kxb@_at@ycWS-%VOC!J5LR>EnH~Bt~gN`EKw$y;5?kZZ>h&t9+%_T zy^F`fx?QEwesF9X{4^Rc~FvacmY=wB?aQ zUbbw;uo;l$7>}3C66i)LX&m{^lCE-7ZQkg29or5Uq4$St+_255tmf2gyl9gS$Bu+i zuH`hIJUE_?s2_%=mum%+_P*xMo=AX-i~!bGtcsgjrBS~uh8izuAQl9nV`UHF8NN7o znbl;Bng^#b!;6^|AI6`Gb1?q=Y`W4c5=CX*s7~NcbZFOxkvT0mK{6I|GFq{H)+OS0 zD2asEE7J*9RX8Wo2=-S-!^4v;oa5R6;gQ^QQ0n7z_bpyaI$p%_oF^sls`MZ?>beie zQ)9T)x}IBRlf>!1<#YeV9z!epgIr+j1~9li7Osv8Lzl8V@X^l!zwm6Z{GE+58S-40 zR~lkiPxFtXwJ=`%G;H@yM~7#L(BTjS>Ua5A%A88b`oak&9xB02tbp4!e;`CFZNRTr zUy-lB*TM;x^`QIA4sJ{=<*ayp{vjUjLeH^3a>Kv13J zhnq}uP|J6)pm$F_bYHT;Mq3^H@=%(rQf?uU9mj<@S4u;z#8)KKHAyi2el=HRZiM&KM8R}|JXrb9#;-pz zp~GGavy5XgC_W3m7Z<_#C_9u=kHZi9#voW|<0;cBsJk5vCqJFylIt`<<)Q;vA2=eo z=Xn6s`-Y>P{SFk_CCgbki=qf`vvk=0nY(Kwi-yO;(YdAw&G|85I@!eMU7IL4DVzu# z=rzAweV0_q*y4j>^`OF!4G%rqDfE9b1JxHDZzjf?c*iXV2APbWnsZCRqpV`gFIe|=MU)}E__wA8#hYL z#(>5EL5Sic+5^Y_|h;;7NzJsdKttSi=)4q64sD1Y#1ww)&&#c`n`?tc#A!# z`OBj7&@gO0{gOnC@x{`eEnLdu<>d8?qg+<+NBHFv1_v&tVyL+}^jJR-G~DSU*Z6#f zYhHXLud@rtSYZJ^=kov^=WSR`T_w2xz%ah2%GB;HL?>uux?^oQ})IYq`c;hpGaE-S+}(E?yv?UJfP)*J8+y66pQ#y=lpc z$DCQ{ZayY09xA$(@s9O=IJvX{XWg*oQpa5;jRxCsE6?q-QNEjq7`a)FT6~chUzC9C zi)ygPy#Q9nc9Us8P0^-JA0*yIa%Urkle5mFxcyI*;T!j!TRY4Ra9tkn=U5C6>@FD?Be+dp~J z|3l7+|55!fQ1flP&92O>q48qVD3{a9w62#3h|+1RQNJRwZR0|#hZpX(*j=k;qI|aY zza;cWT6|u2kv|&tzVy#c$nW`6y3Cs~hy%KYIMn_WxJ@_mIG> z8B?A9x>L8mZ}*>m%J^^n`9}(2UTfF=RsZu;@_O^nj{nP2R7CuL&|mq#^*3|hpA&li zecu0_{z_E+Y531||9#m1EB>2E;NSK4pZ@TD`Tr;Y-azZga0NC|9NlyyS!vXtp6o}zs3hjyp)5zf_(nkpvI32 z{(9E`n*Yf9&ztKXxr_7L69@APe)_BaKaVf|y}kUu&Lhun{zzr${9v+1DhI?6NOuAqGQZo3W--j>>+b7+dxjlzo_S3JEb; zM|LSQ)}a~3SpSdy=bm%#J@+j4-p`%SXUvQDectDNp6~Db`+mO@X>53jlY@@~f*?*k zU2RhcV#)yT)LlEkU(CDmPJs_)pNm#LW^iX8f2TXQAOj~KFL$_)yX$okzgu?@u5eFT zDVZ};3a3SG`}lYvl%=ITemO%5e#b@n%FAQsU=(&QU26mcaXW3lnesLATp@^GP*3~3 zc>sEDIMn^>(nj+lQBp%HV{Y!U2VA=Tw8(W zq` zEgWKkuIv?o!q}Nvp);L>s4(g2+1Z}BW0!t>_UvRj!9|S=`so-6ZDVVDkmLT3ao&q0 zB{eC{OVI+IvEN-NY6hd`lh9>CpQuOUeqg>EwsaT@D?Gpz@#M)9-_Eu6QMR2> zwfw%n?dth32s-{}TmS8(_&aj$B3C*2&b^~1&#y}2j~rPK+&6V!mhYc|^4Eu~=96Dg zDzq$Fu6wJL^u3-`xpRB6r!|WYZyM9zBk$iB@bJklQ<1$tz=kEOhT_Nccu2xqD-lb( zG_@A@{07i}Y1r3Ix^an@_4Oxg=)EN&a<3CaJ0{yxFqa^nhc17slcVEIHf7FHLF$h0 ztAdRs~vW_gAMnVIL=*w|V^PC%L*dI4b;MOK-~$$Y`&DY?w*Lz zC=L&2UZRXT0`64~Sh)6lk`2mcCos9eU}h#JaiAd(zihyW#l2+&^+Hm5s6*iLY$pJF zUV&NO^!sPBmTIRVk>G%k{aV)6&stksv2_HcylsYzQCqg6HBIt52AMDzi~+1~;bcc@ zpl>%b)TN{4$l~ViZjL~dfjZ8rVq<1H$je(;Sy|a8H#ax;Q2VG1KP0jtc1{y8eSG%% z`ufvBDwUc=4>q}VD~I{6rVszwo4Q8<$+e#RWVODNVAoyL_#m^P3Mi&KCp|msQIUZPvu~VB)O9MP1JUsX>2hFX~ff3r6TMJ z{SQe;Gt)P2^gKeN1qd)~cjzWnm;iggC7ArZo~fCl0RHpLDp(VizaSre2jFk0B{v{- zDm8s;h{~5v*zN+f&P&2g6~*F?AC=Q2%tu4k=DgMVXj9!2Hbk?gz!6^}1BLl?wIqYzTX&0nX7{YU2#o8z);DR{sMFK;xXzEJ|oVLxSYzIe-U z`2NHP+5e)0WP;6Ws*pOCMcQ1uwYEIxjp09YEsP`=qrRF?l1mUbTCU4g!ELV2q!Akt z;~kVBl1duUCoeAz)r$JQybnK?;bxyj9)!a>IB>C(yKje#kCEN9rwJs*&y9eJtSv77Hfkw+2~>(AFJtEwb;A{*VIFj~?A zWRN0nAdO#n{^G?8T927gL2jl+y9bJ!4s|X_;BX*^t4o{!}I6Qwc3)TV?qQXwSU+P*|EfL%Fm8BL`WzoSS~Fs z*^f}@Yd|p_EMtPY9J^S2Ru-JVbnJfVc#G?j)u0PDsiwHPyZ3BvtUXCc$O2WOw%E8o zS=J>w{B;H&A0KU@fgASuU0kxVubbA+olv$s;Ko}2l6f3`gxs8t3y}pyt41F}D0_{C zIRuQeZC7ljv94L}l}@A3RWruMW}^Woq>KC~MMwNGH#fJs@4i+ht5H`)Wu-g;22{ZW zsz~O>+s2Awm6afM0t_FJ6EAVq%8HC^ulAn!ggRaFiD422`bP?=ClyNFexfp(mn%Y= zfmJ7h68=5i|9jZ_#T*nrh!P5wb4T+MdP@WQw?=qZW*oPsk?jda>Ql(}5nP~J$?M(; zw|*#0DDsz!wjITvj{LLjfFR4ZBRnX; zV}P=Nv?9PPitUaNZ+xe&;y?cwHat{=P%CkT!5+=L^qTvX$rcV|00bL6J#!w^Y-?Lv zH)wcQEiHM=2+w3)%pDwx@3QQiUY#i+qLmOmU0v}XGMS(Pf?1fGo7?t(him;|q>fZ& z|9N!om1jIu+~}>g#HlESkqGDn6IATiaH{z z6W=p5R0RCkDHRnJ=h5}`AUOpEe+Kf@uY&fIAUhPR^@+x_;xwL-wHZ&i1@xw@L1IXwFn!Pp1^ zB^B@%g0jyT5yH?2o9*k|KR&M-LFwPWe_w_kBdp;Nyh<|x?V47J#VP|it}7-c7WwQj z6njWjjpdZIH1TZ|e}%`OJaDr*jzo4==IPP;dSJ9B3F#$Y+L9#1#V=V~TcgOC5$2|* zZ&b!0NJf>7TtiAr5FJJk)MTnk9P1sp)mJh^r-=2N6=%<$J?GLPP*GI{1KxIZm=cl{ z>%;_2HIUGVz6(JPqC6%ddrO5_EU)$Co1_totX{sMCNrp{K!=2Ap}<)g0xV>y(6MRB z3i#V7nBW3(+{+5wpBI-7d;OoesBciVY}f&bvTgsQ>Hanh_|pRW%k}*~9Vw0392j@@ z{l`zp%9;U`Co3Ux0smiL2D=gXnaa3cdGXO9F`wIz<}~#{2Cy$6N`TSlhX-m9c^#=L zc_+n9woOW*TD#(B@aB5U3aRbZQc&N#Ztf z#;)e;tI?h7bzX|@o5A|>;8j^TDn+jtrEfV+$^5I-qvnvnABS820~Bhcf}N=UTb z)(RAepek~ayahTY6w$=}(f1IB7z~EvzEJ=(_WLUBLV9UFAAHMCHk%dK{TyS{s zg9$I8=5f{N1|+z;DCUC5-s)L(wRu}FC=AB3Eg^LaAV7l{2b>L9Pt*akzrRV+<>t(0 z96J-_<)K^Pq6s9|KQ4^!GYFVDLm(2fR+nb-K7G0lgiK)HG2dDsBHw{$a0gN?Yhk)f-QXe$#jg&7%|8*6k+SJwhAA=TTm?mYJMimEGP_ju95 z-MI#3N96TD2at1m!wOafkgXAbuDQLv{d;wn4zvkC)($R#{F#z^2gKxi6Mg+hosBKt zV$I`ef%7$EK~@0&osIVTkq~Zmy3ht6RAW)%fB|~n@#4jcK!d%A7F2Oov#F|G>a+Ew zkvqxD^!lw~RCYG(FZ$16Ro6RUzPerIuHDx=Vt}a4;TOMx|6St15&*nuZ~5W3sgvz5 z3JN+wc6u&w*}b7)Kjm`tJyA(uvnGSAYW*;sjlAQgKQ%_~w+A#un~09);^nw+2Mp-A z`7j&=DaF8;qxP7^4<$<4J{R`)^TS>{Lk?lIIqJYwkYBT@Ya8=VEFEN?mIekbDk_qO z>X6i-$46wZOuoD`+b<*D(%aLcNb1jJR( zGF2oJX(lU1{cLip4j?Ug_x_9&INthFj8N}>Bh}2>d91#0$V%o}Sy@c8Z0FF>X+8Ti z;q+mD%u{)fWM@Je23T{sbLYq)5HbOQ0(iFG?IdiGrx*mY`bko~g8oC9KvL@}hpN-& z1}#5+{3x@QOJ#iM^^VP^gwSiZBQ~wfSS|s@3=lLn14`_6-2BSh;Cf?e1sV?p3B~hJ zA>cbef+y$Re+IWa087>g#gE@4vx9tse}mfp@`jw}kYdzf8Li&l-egtetMQvHCP2*r z7r&4kAV@Qn@)I~DWq0`7saK7SGg=bFw`mk`GkIR7wr8TAEh#0X&;f_CUyuU9^C1v5 zWEG$u%+9(;@yT5VR;DlODPvY(Y`yx!!g#}zl$4Z2QgghRetGbkA8uoLP^KO)c6iV9 z?8h=?XhQcC(5;In~ux@u(ighY6ORD!5}5kVT-MbPfW_0-rhY@jMMJv#H9y zmpM5(Pn|eXD%5nv$tg4Z^|kkmeUaMbK#RaO*A;_SO2M9|S&$+ShWd%8I{|oUeYWs| z($X`Nn;--%G)h;OAziSyPX)Q>j~1kcFVPn)mnoytdTKL4r6IhHPx{MU69Bk98y;}Z zr*Ez2*;adHwsmy)fv(b*89MIrWt>7CI$#YfyoISX2)T*bw{s$s<8j1NxJapr&D;Zi9Is&-=2(-+yX)WG}MU3vA!~ zwnCT#NkwPyAxWFhASRg}LCr{3`BNM$O-(<6)MrngVO^VG#Of-Fo{+xYI5%8N+@3k; zlr_M6*6Jl3KVl>#A;$a}jo3CL!yhs)*n=7w2D~r~a#GBtX+Myyrc0bS;RU`&@V&Q# z^Un6~pvhMO(j5s|^AMj3_ZX=|cGOVeO%4@qPud6sf57twX{sN=3_o(EvL-2W z0gLIaFywV_1`xuwX0R>2c79;v7^bkkUbG5?MP&8#kkx{<*W4jvcv_Bh4HL_bYU?uR z8bI&^oM03ct_Uu{I|;`P?ts9mgF>$b)P{W`VTlD@S!IQHVdgOSVga=d+ioJ-|GtY_ Z(HPTt5@%w&w-W*{y^Dt0#ah?G{}1wrRt^9F literal 0 HcmV?d00001 diff --git a/labworks/LW3/images/2.png b/labworks/LW3/images/2.png new file mode 100644 index 0000000000000000000000000000000000000000..ae851e60d3afe2ef1a57a4de465442607c25afcd GIT binary patch literal 7138 zcmds6c|276-#_*cT2z#+Qj$;?*_Sp;vSpcKERiHxGA4~ZDwQ=!C1z6DHTGqQNwOqN z*(Spv+h8(cFjN;+)#i~7XKlr2JcjAnnrS}Ct|8u^skjXhepUd8Um))JEuDbdn+`YY& z6b>C!P(2`Z(a+BZp`obg`C|_SZ(ldXQ-!;&z)^U849_AUNa!5v$(E&?=?+0VOpT5o zvAUKrMGn2(IWOKgL)`LN?{a=_dbLf+r|{-o;i4yrS>h)3;d~7{?;8AQlqsKK!e$P2=6JPq9Uz{KjR;Bv2WCs}) z)a3vz$#*iJYX+vP2FfMz3!@C$drDB7x(o#ApGih?Kw(jv**KwtM<6!n)CN5W+RV8D zdd>OQO%KngeziV!?3jk%czkg&=+c;o!Q_{e6c13O?ICduKSRrm zQ-xj}kk54uO-&Wl>_{=qtg?I%yzQkO1ih_Y48h182%Dr*k)sb_msY;b?BBn?-9R#U zu5|KRuK;wqjDzFeid&o5gNF~PP4{-+Q4@!plzn**diQI= ztgW}8wAIwcXX$i%dwVj<<5*h!{kKjBMWQWqj;4K34;^S^3XXSXTarpW9-cHd-rd{Y z-fm@Un=>{xrW89pJq=S6i`@=|b#7xoODlAOikezhUteF=6b^@*oSf7c{#IG3!Nq>P zX^>Y9s!)5R%LTKu%QfF8ESj2{+AYrp>Ff2aNtj=~TGkLP`kY3iWlfREWIpZ)H?e8P z@+f0@n9L1Hy{l&mUhJ#5lC0^E-M)SMuHIX>Zgqb6@N{Ts=o&^4I(Tx=`8_w1lefz| z*1%Q!d?LnLpJZ-xxOSwvx_YTrC?x)N2RKpM4bBhk>BjRtZkUNXGH7!c>>(Dv8sOPm zHWkgY8G^PcVi0X-RcBm3`<%J1_qtL5dd?&3JT->f4)hf&lnPDqa^J!LL4g%}MD4ZrvD<>Q|UUFswpVX#a+sSTn4On3Z^p)hG-29%SR z*U6}1Xt$!Z?M6pO1D2=CyE;0atM*@W`84d|;jxA9=C0?(#Y+8PEECM%U<8|5S~|O6 zjxWo~%FZ#CnIVhJ)#K%Ckl}B6j&|<62IA)HaWnM~7_7E}wm6#s!Jg53O$PtBv3(z1;JgxORZm{kxp;G1a9os4lghs09YvO=jEo$1tPMLl0r%U0DmFHBvG}qyv}GlXtdQi}<$aVjiLm(OMI{tVNVkzrypsar|Ge z;fE63Ak-IacVfR;caDplje0mN@!*xAw~rR<+7p810e9{0<1NA6zeV>%YY*W{sdAqs!{rip^yqj5^ z3?S2(>j>%H{VJvhs4rQ`Ef(lRBpDwtf2sQ0P*lL;=)+Q%MnRJlH46X$@V~0T3v5t! z9bNUAjg3uCQIYSb;5PN@uW$I5dI%v~7q7mBIR;w;Dkl}WM$sy%SbpkODE_yhB~fz& zgUHIt%4g`)yqxSnfleb3^a2$olgSrZXTbr*FAZ(i1A>z9;=35!3wE^r6DHkQm~>qg zhI@LxJep>H-tX#F+j34wgzbvJQ>TObj3#NcSW-WkEZ)Pg4#7K$ii&i z*viTMTZDzjXBs78At5ze7e2X6 zPEBzcc>BQ$?imd->A%gQP#DP>f;VS>96t)AuNF<6pPbtad zDu0=$o1?e>9L;|-_W#WQ{n)G4`Guho(J?gm6jFEPvye9NTM(d>Hg$r^J1`Yo@^_`S-tb<6X^PrLOL8VAWIM(57O}sd_7A;6bXmht*n2N{B!j?} z*(NjAFx8_;c3Q*&5%T^ zoGjRG+~lSg6BE*!BLCTjjTwn>R;Y-P{0RJU=o21hY*NdOSiBogbeY0MGbv+!DB_ zjRfynaorHDNw18b$SNu-n(MSQbAOkxhlNRRZ=y?_c7~|Zg{)Vvw6HN8kiIH`tpq_a zB?nMn-Xl5&g%k%Z`o26{tRKjrbxnt^1gu|*NC;KH5Bz~DG(nw`_vBlV zk6NCdloOdde$yBMBWXzvoUW$e8YpxWwx`7XJ|$UEcl^f4R=%5Ui#Q#R+V6DvW7_^l zQ~uYz-ZJHIY|?SOoA;h6hf=oq|EhQa?Tde7lXvDE`Hgxty-l-Q{`H3c;9%}|aYJ|I zw1_EMsNXUW%;kZ#*lfYVcg@YSa7#dKVWzhjn6;HgL@W4B;q(jt82%riU-=GmiHKi- zTiV-C;V$$PxuQL!Ct_6lZ-Z0frpkJ?i099rmwtNxbMWjt8MFt9MB4O$SD*i<2%E84 z0gm6{{mNouVuCf=&rU>jl1ST;ryLzIIXO9gK!B)4?-e={_84~pawld02E}ATmo8m8 zZEgL)*4B28RyBRe$w?0k1Yq45G5Xg!Au6y)of#%iSk~%Tq~JuG=5%!6FckK&wd2@2 zVE&>4ssT}tj*MI+V(s_K%3ACbZl4ZeXnKAs*g1QB0wkCDR__o?d3pJzg>t+&z73p| z#1+gf%y(0oxt1I5KSfHvex2<>Qj&h`V|7FZOD{mYITxxQ8j64O*{2hNUer9|xOnlR zp^)}myjSJK-qvIl}msorw4{OSb~mx}q%0JLq64nfb4oeJGpT3Ko9T|J*v<~@LYcVEV!j3?qqss{3; zwzjr~|B*i;QQhhR{D2~Wi17|6%%Y`3JRV`%)zw9Mg(~h3T?+=Xc6i8~crFM? zO=aEPHsWeNdiC}7GZP|E{3b0jo3*vId)+MoQYA7MB+A_wDknRe$)kfuuIuSB`Vev8 zMkGFXkRBbqUi<57j{OP>V<5Ka37fH%TxbQFxUxupUY2iPWg};k7cb46gyB!y+9oF* zIQwjMHG~x}Rq=}^@MJFNg`gSRNQ&n4At1-F;NWUtHC(*-GUe?nI}xqKMgKW#aD!RX zH5{kA0Kb1X%8Z+x4VcW9#rtMD6S%!e)SWgvRK3Is5j#~1wu=2zp#Cd%f0(U*p*lAR zF(bY>$73L-x+6bZm0X)~CaB<~6Ww;+^Kb;c zRaNHc{ck-r!Bv#xUT-`Z(F*R1HqmKr-FJWebMF6U26Q^qF0AC1g&A**i`wz0-PQfx>AP_*r0eopARxT`F~&P zpR50S0N4pm3B@P=uH65Y7+Szc0Ym$&q4|N_Fi9D5nxhNru~aT6=d`hLRDUqTUSR$D zth~Haz|dMWvIIaQ=$p^^JcnuxtO*bpyzwisS0KY@5vkoTElo{huL3kDBqTH~7%NsQ zXL!Hogy32V<4RA>_eoE*T(h&Gp&nb7;Gmm|yuo zNLAHD#*=4d_}OMTFF-P0)BV*nq0ny;Re+EChU%jTO9-2nwxiOAMAmcfuGilutl<{> zR!k4X7Qc=R69lL?C|cOGv|1xyPfyP}+BB7lNHgE}8z^;JWnyYU!?I1MZJQoihhym| z5?R_GK$Z6#sIk8X!%>pT)4K*iDZ z=~GsCcsRZLOHZ*uLgK@R+bknM6Eh+k23D`+TphP3xzZXCF<_(wX^=ixIG>uDA{CsA zs97dYPtLwqB=%Pa&I5|geevRWu^Yj(Nf&~g5@%;|ac#3Y1AsYG5p94%UOz}otjNnd zKw&JCqeYeap2z6~^fTD-2ZZ?^LPwg$}*YY`~nKQ0kRdOcY4>aMzde8Rtzh_ z;+!pqpxY62rjA)9q;d7jBP2f*rlvM9jldWe*~O-%?POJKU{PilgDjRo#?CnP_*q+< zsq6XkBFKwzD7BdH4|&nCTJ=nq##mY4Pu$(z@C4j>&cG#G(0?g|Rt_O?AA~duM<+)o z2~(Hvk79JBo|I3&O9D+^4SHRFo#ppMtl35w%cYmP_AfF+s5Yk#31$9x#AKihD#8@{zJw2U-55=1l^ZM1G&J;S=ixLe^oVW>I zpZ+_N?b&(7IVctNNH=s1o7pSA8Ou=MsSDk`?6mmcV>esgJktYiQZriSmx zZKTI;8p$KS>vLV??qS8y#VDjPFR`~bR~<2yRZ|o4iJ1$_?~YQe$$ID*a#r)|mk$7v z)(#HXnwpx8H08oJRiOkc3yY1&;LD%@QbQ4cfi4ousR@+K@MK`U(4o_2CBBWX5VL_~$?8=SN(BW6*Yk8td07p9E zAS5VQxv~-jgTdTBbv4<6Yj^^pGjd0UG_LiDs)2)$fB??v;5a&Tb+M@ogg_PyfWa5g z5EFGw<)Nh5)dbp{Gt)up$UHJAdcIbeL(XM!J2~)$EcIpv62dMvNN$pqDDi=@ytIl;?}8D>vnnlC2LIRDvq0n=fRUF zJ4&@xRbioP%L6f$MHYV)ZxhKL*pJ}0&VvXrk!0uf5p*SqXtWm@eFuwGFxtMb^v!vo z{@Jr~_2DJ%9divkyvIQXr`KcT}e5p2^>sIO> zePBEnrh5G?f&>E;+@3^&vQcrCLd8~@qEIN?0;lVw-d^yIxqDuSGe&D$;eS-shz838 zf4DMz`#q5@EvM{*=esU>cocipw`?Oq#Ky;b{QM7q2qX{<{z31-Uu$_R90xY7=LTyp z3xdyaaZC=eu4n9=8jJ4}t%%3kc|KHJ8CLeE!Bv!%kC%a!$xcf<0{q*p)E>={l?w1t zfXi|t-+de&&dwE4n?>C%Cg{-^E5406f931o5zr|rr(=aEDLJ{hr6~G^>b2G7{rmRa zCh3Ah#)xYko(#C?>DhIigXi>QfZBl8dN%@EJ0THHjF`9F;MnMqUp=-Gf(ND~b$R5z zSs$1-%5O?a_Mj;TD4uN8T`lyueA!Q2T%1-Xr0WMJR6$d-S6toqZDr{V7TNYz2bQy* z_eVk&-#b=X z%@4dLJF{s_#(=-3Kg|!U7q+6}Qvvmx=73g7X(_7H1i&JOa4vqhhexhw2d@tnrFLcLhMb%n0u;TzKuVA- zX8@XS?`EbM$!BdPp$|yx?nV&q+L_}9y1oP78dUqzA398KRdo0wD5-Oq=*OPoEg>kT zHV6tII0$_7Wu_Ov4eg_WBr?sssca^HkSYScibz;hl7jRu{fg)gh4xf*lB(lvI3e(3 Nbi(vF_NY_%e*xKZg2w;= literal 0 HcmV?d00001 diff --git a/labworks/LW3/images/3.png b/labworks/LW3/images/3.png new file mode 100644 index 0000000000000000000000000000000000000000..6f2b698e9305d2edbdd3dc65d4a1de69f8569203 GIT binary patch literal 31877 zcma&ObzD{5_B{-uNTbpqpduh4NW-B)x|B}o?rsneX%LZaq`Nx=>F)0C?)SqQvHWtkzjyWAA`Da{1$6ZrS+^v@|mwkTT7z9u_zK{K@8a?NBF%kiV|;qpuJB zqW}S9e#iJ7Ta0yt>WJ*lqfd_({Wa18C9eA{ISNqI($Z4Xr&x<}C~n;%)vq)gN5+cdX6#)|(n z2y(hI+vBPZ1R)YdW2$fPNq*gXg@#aL?}|QLes_+om2vW~(MZ+f0fVMesNELs?>4qN z%KU4zDj&qAXvoksWY2{=mPy7S{vJRkIOxE6+C0mRd-?lU!UwT0;c!TM?t=}VV#8vf z18>F~gGi}R5au!HLdZUcv>I}sK|mjs(L_OXd${D29VKkio1q`4V_s}00W750oR1Z7 zhK!ZTU?uW`bzQFB-PbR7W`A9=^A35eAxoej2WLnI##1fQjgKsQb>qJLeyhrA zYjYd@B#F+6?Mb?AeE6SKqUo|JR7US-VoN=s$jBa$W}7(>CW9kl6H}DEAXt`sN?&x` z^TzIWxj>X-ZAhBU&{qAPX}FAS`^^3DoUxw!1nHl@90stse(0M|7|Adg&hfnq_Dy;= z@-gMdBzaTeOXvQ*I>y}(;hyHH;m|F){TCNQrn@Ek{j}sy`9s!vM~$ZI_PX`9#WIv2 z+;Nq+dBPA4tS3`qdqB5Iq+`)3##N)u4GAyat zQGa#!1Krj|ZiB&W#c&5ogS@!XN?MQ8PLW|0iI;GD^;a|!vCJ(x^aJ08(96x|b`R~6HxuE9 z=;fOGALCHgcAri}6W#Y#q>Apk0izfs-<4$;`$C>@qHB}eZ7FL^^5AeiJ&q$~_G+O_ zSyI_LEiz2P(lxU{c85n%S-CS`ttN_I*IzsCLqUf5T)oLe@rvh$n5gJ03JOb?az$$Q znrp6tj1o6d1hE2h&)%f|LN&ymy>@cz#K(2y(}$Ay1RoF^^Qxt zE+dRtJ7=%7#an$ubw^0#x03qsc3^Vu!n;33rY(@eQjDtGjXA%8B+}13UT5$Nb~f34 zzDfqUFputTaT8_&O-)V7rJqer=Qn3_v{77KTnW((`tpt!w*&IKo;OL0MesswgeF z!qiP#-$z05XnODIY1OtbadE0?7aToE;0j2qoFq*T(>Hp03BzlzF>AecmTwn$SGhbI%pOVQsu!T-S|dgh~VPJlsw`mne9?OFY0;d2a}m)7SB3_hn(RmS4*WF_%s z>i5ScA+#+z<&W{KcUgRd!UuC*A3L(a(@WRN`iXRA8I{UQl4QhbwuQLqq&h6@7=Q0m zW3$oApHML0)(m_8Dpa2R6T$WFz|dl@);svl+z-GeWP2=|KIO4q74_kQ%=x&fI_4u%z`VRMy8Bk38%y|Zs;J~zc{cz2C1Y;uj;v@ly zBDQYg$`EFhkC5vzv(_aJtAq@}s5{169yo#!aZ%D&&7y;D=ILkw&&h{MYwi~xa>DRRJHD5qE;;Yh(#s8f3?@3 z-XA$%K#h$I3kyp>l@=Wif>qJ{-#$y z4^C>XM-Q$!*f}RNMvZcf-q*FYfwdqdCIE`9$pqBS zuat|*$&5qUY`pf~dh*%tte#XkuFn(71fK^!;EvC-l zo)CZ{7Cr;nI$`KV`HETA!6h?dK(AAw^pFdVrZzK^hy??r)c*tnjk}9Ah?_?<_y3$x z_88AXH!~QOfccHZJkJXfl7S7IT;;OP4QGM(QCzN&$B!R7I6Dtjn5zdrWm{yFke9~> zE9>XnT;h)(Jc1!a5^iqwLyQeKrvzi_?wn*{ewmrCR(s=Bc8Wv)-0gRJ$IM_)&wCL2 z-R_#bdgp+8DvHweN0kUcP);=yYPlY%>01 zyhxjHPK6r#@?=XWj7(y@%owMj;TFQ6*FFCeojX@PcTgM(D~CO&%xZ$b&rZr5g@2Rh z17wGT792cAgGVrT*K6E}$jI6w*>Wg^kZ)l16zlci+ij2Yf*c6zaJ5rWb#pr9xD>?V z8yKjwF_;E0-eCuMB6P)Fo$iQ;i|gE8Ur37lOcU;bLe>fm85x9_B-rFRsA ziMb_>j3`~NPHh8`5fGAuLWn?Cc<}MHO8FyP+;!pmFqfx00UrwVr^-!(4b3VS;A?AZ zpAJE9n%@U4G(KK!#o-qUUcfeSw|i!z3*+nW|Ki!RA9T%aZ3^rW!^5&LO-)U4tv=q~ zZ1rLi5~Pfb!yC@%=;)qaUh(NwE8*+s_Z)1s-5Ojt{J-Q%MaWQan_7=}vUECfQG|$GU zSR>o>nwqiuWu3O)+88RoCh3=FGgNYOJPW2TnDyody?<2f! zWI`2^Kk^Bqv3hgmLik+w%v=X&GW zHzv!d)N1S=Xf%C7wAq;q-x$h(+n=`X0|;1(-fmklzy8wb@aRaXL=TlLtfMF}O)PRS zU4p=@{zA{J;l?h%W*3s7k8uC~{X)APW$63|smbAVLO+_z)v3&k>VEhYiphAP2Z#yr z;53%2-FWi(svGUTo1I^ZqH~q7yC+u~VW{J#qm0eU`|mucK36Vp8KNYhHnzbI9<9 zP3`qz7xX7w665L9?qc1pTRYBph^-b#5F`FO1+sZ~mBT~PMzKB_@e%Pz6LkZ9bdv9F zwkOtwYRo3HPAO@I50q6g7WLv^upT#6-@&oF8ce1~C4I4;vu&UYY2tt*M~kM3s^{uo zEDwvySCy8OBUzDk&r)XCx0lk-M!s!iMj`qVwxEgvkm=j9%v=7KMqLjX@CWjpVL8pq zRFAK=QP4g4;&RsS5k#=n=Y*72?z~K=iu@)sqPnqS!?uTWzIA;vf@PZy1))xZVJ%h% zVcM?6E6(mu+z*!O%6x{=1VHXIu(KJj5^l>e>Q+}*d*8w1;=;k8-2LG-zD&1!N{f{kmB7h7!lR3F0=hk$b?y)iv4wEZS z+dUZy7XxS}|Jdqlj7O*1`v#NFZxqX`tB}vj%Q}$}`v1alV~tW7GV4}qTo3J{)le%0 zr@3i@&c+C}-Zxdj&fn>!?r+DE!y1g$edKmy2@P}HO|(3N=LWbpMFmUUrb+?w8Z6w6 zPSO=wCTYo&$WxiBBix`?eE01o1!88MMNb{HJEPTpA_n`QjvqSZC8q)N_)2c?Jrai6 z`dZ>*wp)r^XU`ufBbusyCY|CD^vBU3>SPf(EIKsw;_E^{D}#J)Kr)pTbg-d-Q8?)( zsg|R&P7KsL4#?=}-Ph@evw#n7Z|+*ZjK2>$n+Nadpn?(t-PF1ig8*0GO7wj+EnpQ;t?#W2?sqzc+w*(k*m6B2zBfGp55%9 z4Ka?p3E07X#N7t>f4n}^rL$}lDbGjMm}M9U-diFzNBY5!A?@g(HS&R8^UaU0JMqPx zweJpk8dTzX?5=w~TIZ<@Oos$8{{hiTuB#9LMq_JHk2G?g5)m&GI?WIp(!vAPYZheN zAFXDQFA)}Jbp#TBXwSksT6}%&5=_L2#50z!77gk#*URJQtgKP%>tcJ`*a6-jKf;*l zJR*YZZ2Qh7O3Jc-LOu@JPO(GaL$HL+k#6mCkuWpM@9MiM5O1l{+6~@1IIX)jo=Qk#LlGm0C$Yz3Lx8F^bO5_Ue!wQjl%H_f;7D4@f>I8K6le0)f zaK;qTRJ|l@g9B6#^lLZeokukLj-H*IBFln-i;e<_b^w=hvjl^HDy5 z1Rm&>`Cf|t!Jh;W6Pj9+b|@M2i(E5n%XHCHftgBuj8cMn_xpxb(2-dMaPJL5=@ zwD1j2g`2HC(;`75jgj+P2^ONq+izEDN)d%+wQO%5WcfLM5$2wkS3<4cW{!NrdgA5x zwFKUCGQx6XSQX!f8jjLE`CX()RVks`JY%mslJOq$^EG=ZGqq^RcPhqtEi)j|o^gfp zb_IJgB2>_8%gU7JB4(DI$c0ColIOLimYLe$RWdrwB#6ldJP`%7$GG9@lG5Wih~C$z z+g8`5LEIZYN-A!n_A6Q@Y4$j=;+k=fKjT?Ux#_CUtgQ~|8N66%J~0;-m@!X_jK-7xlQ`zs|!6|j`25=-&J zM$6SQ#_!du4SqSWFV*Sn*Tdz&)N@bxG*Dx9x57^9Ve5%K;n(*xc_n~J-w-A5*4BBLEkvSUqw&x}FI zRc}bBtYj@Wn-S&Xy9bcm@zz*~r{^Tw!APgJ6jFPtt~R7@^bl$ zHh)u033Tvbe62JE$mz75!`4o9etPyeAKtiKmGb1rhj}&1hB!}LqrTpiQV!e@onKN< zSYKT+SbLk17S-A#sd)u)KaHzUS3{&s;92i{r=B&buhA33B$*gVt;AhfMN2iSuMM>GM>?+MsHPwf8J3ib%P8Rc zNt3qi-iLmtHxY#o?n~Xgm&|E_z*W+X= zt}p<&(_XrYh#-=ZuAymQi_ORijg|c)(^D4lNR^!>)|B@Cq3xc94ZL@fo$g!oS1+6! z)*cLzxo${=u_Mvp_64zDN2BXLfJ_GU6oj9D$`o7D%ji#)pzA|3OSXH3rtC-YviMt@ zI#fO&0+9`vHSbRhsjV`8V6yYk-u(D)wL{<99Y6e?wcKn z>t?`V4$I;dqbpmNef!Qg+`fT(8&`k-WAGTZ#ag@guE8W?jarS|hMlSl3oqv`PiFLY zURBknpjOi!N|y+iWYF!zBomLCKQ}2-^!2a4#z-v_?+cylwyC4(vs4L_%;;aKcBxky zoG*@48G^D%**A6$=p~*$O3920ZP5~f)#5h!jv|*K(etNi_scA~ifm$yl81&IgZl(F z;N9FxVe3})hmx!f^V;&Tl&2F*al@D?ntMc(*Yc{wt1})LcC?E1NpF?n$Sew~x1JiV zFz!yUgo$t&X|>cmkCD6&gNd_;@a`pErW(MP+9#VMP^jD*MAb0TZosI;IJ(W<{67#) z0E^skd8kZp;gS$Hppo`Z%Ldl+pF&Q$^*6nGj7;P8nepGl+~HC=l5+@yuy&^>AA`y^ z)|d<8ddHrGO}vZdP@q(*HL9mi6^G?PP`MUb#hCK+FFa%2A?P4W(KCq?8maw^L?E8( zRo;%2a*&Ael-cw)=H+yFPhcn==E@c#5=FyK@v}Z2!y?GYf^uM1<_`RUe39f4Bt(|>1XGLDuz^L!r{znS zqo%W?8iI*|?qE~ceII3tZU&3%B)=?lX6>`jlUrpf5d}+Q7q^({`1?qu7`9?`@d-sq z+yw}d*JA{j2J}2PQ!$jKo2tzKom#uNnXCdQhVXk1X|&RmR(( zgZD3U-;o;*YKf=Z4pR81OuA}FaU9(5ig>-WRnU+Q3fkZUKs`A)t3$d<6{$gqV?pAz z-=Af#QS*dj|H`n8zmi8+iW!ry68$gqLvwpuc9c5eZ{4DXNOEvobsdvY>?tijTU_}E z{sdsZzBk`WU~Yro;BcTN7>N7+3>Kh^%nB&d$Y%M)+3=~wtpCdL!^{eEw9hKAkw6w# zV1+VG9DJhxNfHV7@caclz#NMEP5GEf{(%Nr;Hy9A18L2Swl*%gTB@~Z!bCilIVdU$ zx3;d%aJH7Mp!U#zh`|n1K=bl=xlR?EIaR>j4|xXdQFx3{ zjtvfvj8DT4{vaqUCb)c*5jy?er`WHRo7wkje>QqO1avc+^;+-BPQ{#^ID`GJDmIO3 zJ0SD=05PzCaFFbNcZ-RG!=8=@j(c^sNB;bIjh7z@dE}XhS{`pEz!OAbZ5%rP}$=FGWPyr04=>i|1+4|i$3=!*x0SvayhsV zn^zCfiF80B*d8zP+MTI^+drK$w+7tK5g7MJcuEX=4u8;La=H0)hp~!NCEJ zntERXrxKu5eb9;F=Rw7)3xdeB-IOWJQ*O67z`X$SW-E&P*|U#;$tcwA!iFg~nc&mV zNFsR*vp!Wp>r|Hj*nknm3BV4;_Ae6LON3n3Og>lD&TbjO!ooLg_E}k3 zpFV$vxb7`1@LE_DYRAOEm2 zR@wH?W3zQNUPu)QbGW@&!vmuQL&$Eo-0X(|7$ydnbBq7vg4C6j@zttrV4neg=lIwr zV?{Yn9!!a+M`QOle$$k%{CiiDAxOx`16%P@CGcLbH8W^D;^HU^3k$g_6}<;_En1p@ z>uPRoz4wTKKul5+4P<32@uQ^>Zmo)`je+lNE7&a$elw$)58xi6>5S$oy%iD~s&{oh z-JbY)eQ|`xWP}OxZw_X#SXWF-ODl@m6hAaH6orTb_am5DR$F-$^m^U6v+j4Uot>Sy zEM`vup_W&~j>z*H7N;yO@aA``6Ph>NFoUPM3}8Lz&8AtQtjDnvr~RBO3o;H(?e?4{9YmnYs-{Mn z8vEY8dzGQQ4(l8vXhO1K(-O~&zD-M52ozK5UU!dyB3M34W_Bf$RpD6i1e1shXYWEC zYt-{eIqC<+oT6-j%RdVFFGaV~yKCeA`Pju4)gR3l8cP4FVDyr#2KE2O6~Cfk#u#3U zffa%O=s`kXwRT|R$)Ed@aDTN9hrsgH05zT5V!fqdpxg8CaAKzAn@Ies+S+eBv)h-M zuy|KNn5oY68UqwDb6@w)KfKqNQbC=l;P~<+Afeq%;MkEZ{6{(<>+EXBJ}z-zd~xjm zG%K@E#3@9hC^c({?iNGTo0X@>(PKA>){(Z>jB?C$t)5h7I`&Uxz`NH8NXnEMK4ftV z3;IKGt)#?EhX#A)+0Ag1(`IKOV&BJhs@|5pN-kCG^N82uO2BH&(oPra%Y{YCpV?7L zG{>~P((|0P*JC(M8={UUmQ=lye@Xa;&RFRQENUkWX9+=zY_i-MA3Vo5fx+9Dt2J7x zL5#ujC<6Udwc{%_V)(Fg!$+ zGAA+(%oA^`qms1f+R|s;*M(8RVazR>gPokV16oe%4cV+?a*+|;bvSm{M#!85%Ff^{ zojC5abeSSg>{OnN3G5t=Vf#6|GQF+=0}2sR3Aa?!x~U91Y4`j)Zw-F?1 zX=`8X*6eLEetxdapj1K~Ro3Oj=Gffa)Dc8MF*tDNkqZgp-=c$!>SiWuu=acqh94Gb zoLRKOyragm{YgCLtgB(3UBIK6v{4nqK4P_Ed8kkV@n)8lpEu^A2x5KkMm}Mp$k_V{ zMgujg0o%CgW&Y9kBsXjEWT|Q*7m&n`4{qC*G;X8WllN;1kFC7na9SF)exNEFHDLE8BOkjrDtC zd|_`(+{BXF%1Y|)K|1f&lWx>LwZ^yV>O6+^9wkCFcYZo+Lx<%`b&>Xp z`F?t$m@l2R;X>yPv6Js)Ep+47H)H;zTzEHvVVx`yv%zCfGI4&^a3{gb>#;Nvv5 z+}9n=u*FLM_=!^I5^bU$C_ldeGK2-=J^Ie|#+H>Kp>|v&9OQ$_ zk9ZP>s_%y6+ozKk)H-WoS8NI1v6$ z@&PuwBq^Ss2_+K*2ZLn`lhdqde_O4mgJUVpj#V!G70s-~yAX5ocQ^C}0F8l!R%|-O zOyquT`5B$K*8}b$4J2;>*rAwnaaI4N5qDV!4sBpot48*DsBKO!rnW>qVY#F)m!cwS zSedqXH4sbOfV6m^qCBGf0%o3A?lW7n=%F5QTjf^{PQ!*6-*x2^NwEdB09NOA;e`on zx%!TVsDs0@$I~f#lb_2fcS_eqUy+AR2%p(a=?y{e z5;qMiBO`HMD}Pg90M{J^66`);{SO)+5)XG=HvBJ%xZ|?mQar>c&%O zw;V++abgZl-$e~a>wRmV!r@VDs*V`u#kGoyX&UpvY-Dg4J~CTb(C^bI`PrA_DeL#J zv}y)Ax%$*5x^eON-`6K3eK}O&MLtCNhMnVP>L_x^y4abOfN~u^V`jhkQgP~^MP->f zs(Y_nWn%}=oQ_8L2ZH+u^nGCa?SyG6x;gnPij))sj<3(P94`2Ms&VMn!*nvj&PN|S ze|o(+{aP_`4iE0f7x(zogEH@R)HnOzWv&@H@WF<3RZI*dLJq=K$aedw3@bFNv+yu{hwR-^| z-L(i6v#RCme-ozFmyRj9eF^^s1|M!-PPeP_=ZfNSA2C%`Rnf5A$fqx=4meF5;dV#P zm1w(7QbyUdnb; zkfp#YoZ2ZP^nsGfInZK@W=7(js;a7tCG>yG#Iih+6SD2-HA*HNR>BnwhBF`6*Vn%! zC53%sI?2d&d%lE^{!92T%bD!>k*idqSgeBx%AA(2t}eQI05z|di0?87=Aqnd%=a9R zWH)fI{XX~GFm&$gFPc9;YresKx&+AY?!AV)58oT1j53oTu;ahq~KJUa;DBr~Wq2Wj&Tr@(6}Azp%J` zNYbL@bZ<&|4CkuWdVkh%?JJ9bU16-^2=7VU0TKHrrJ$2!%TTvfnB{g(D)X^>#P zE4z=NtC%tAD$;KK4ow<=h|8|)3$F-5WU%&iTQk#5lrWM+sj*5Os2vQN@QB=)dkj?% z-;;!#n&n8pO-Yxn(MtkJ#ALei!1Le^lw|9ZWyV4G>AdECiQ5m`-&{O z#*{vtQ0gva^7s#S-US^>;VW`eBQ)Sr)p7SE?`2a@a(wtW>#(rWJRntPOxhX{YHDxz zZ@fmi)qtBvgnWBG)7($9L-_Mk<7>H~3}ry+OOHsxr%NUFR$4AafzlPo)CKjI{&d={ zZva978{8&5YELJP*KHuJA;j(zU6oJyTlI?dl->Yc#rn|K&pV7jMmqKT9h{OazL0m; z&zMl4!(#YI0Q{{tdv4H#A30Dg6H0j?+po+vVk=&*B`or0&{B)*xkBW^RI^}><%4s< zDdEf7>*jiQ5A+3=Z-bW7upT?P;9K9?EKC`=H4@=oUi4sUx*=Ej4?%5?bl~A+YyHLL zQjWpLN#(TNi$yJF;2`uOy+U&OV%nmDtcJIlWke3=1&_KoW!|vjL+tjWt<49NIoA90 zy!AJyAVjT1bRlWA1rtJ@H#VEY8^x;)s{f4B45`Bp4rm*Y+PmmfwK^xiw^(IwMQt+^ z`b+pM&?;O24tLc|3X?rG|E#GZD?BI!zOY(>->sJ0_Zx9-TzUm|~40Me1qd z-1DjY+y15^n56gO6kT>Z+8wKK;%-;>pNE!BHIr_(>T>GOUv3ouUcdvCoS?FtC^f{m zxjd=Kg#j`&lrp)Y55-3BS7M_hBx zj)5F)M6K*l-LNQb6GA3M>^)DT`&4zA|9v%43p{xPofY#y*dhuiss4!~^2yUnAM}N> zaH|<^D}&*RPkB-gz7)+26~)bcIQq^TN&mt;KNc?2q~?;Bs?Brm?0mnKVL;q9lg(Vp zP~5==@kpMiacZs8;n1XoDiAz^oUZ)2i7IPyz)0Nhyn1Z2HM&zAfq{e5_7N5i${2vD zwmBzB@EhIH8gnY7SeD2b45mlvKU5#rlo_teSyLQm8VR{OG4t(BdNkfEI{fj8)u}Tp z+LKV0@P4bej!b46DpdMs4qr>BW4{=8vfg~h*-+u!xRNXPZ{Sn)E488qf=Y> z6zbr5anxNJ0hKaQq%9Plo=C5Y1iYgbP>bVR0RcIx+oRvA@p)uUXwql-VuoSUhXJv+ z{zMgu4yXC6Itd5W$0%jO0V}D3;`IZ}PVNz2Wsf=!PaJ$ECr$&oxq?h_;da(JFt20S z+m^<Rt&m?@NSymK-v1g?#)x)46`r7l$9BR6Y|fCD!KIKw0QuLD?a! zGxVg4|1nLr9Yf>y5H3+AB|I?NFR7>ka&xKCh&X&_%+>~ki1QAuzJ`T4UT$P40g8l7 zX2dL<4nGKLk3r2ZjM!j1jE&A8i{ENb`^#TAT)iXu+-#J>X*Q9o~Czt(Ci+ z_@?j-RsCAagt0E?nvgJ05UX%!0tVlX>PSq^ z8T0FUKNauL^!)NR<`WD3jXBP-d`*P>&k*vqz9CY6{o7$<_{CNZ2vqOizsGT{{L-UG zLQh}Z*;RG18aq*AUocb|N+JaHn~+H*sFM4^{J1ptL@>};3Khu$zFm>Yy`EuBx@Dd0 zunn~T%k1vW=apGWlaLuF1iPAFN`K34qxvDK)9?fmNXv7#wuwI@-6==Aa&YCN_e7sy zKY+r0{@qWrO|C$(@|iTC1o5Wd{h0Tc*E z3IVB`f`WqMxSyZVpdZHE+#F)J-3~lKecq|B#1pyVeSHxCOS}OBl~C|gOJ%`-vix18`{V0t5W~EU)ukAt7T^&$r;H>+~n_@?6Av z07tZ9nGqHMYAXOD0{r$F6lJV2t8;EwrcfKxtiw`}(aFdaJB_UfXe`MeAioDaM_Kyk z53-n8SOPpeAGLi$LK@aL>n~Obs_plB>&|AyfXD~{&k6`TRxa+>=a$kkGGMR@v{iX{ zU^tzQH2@O}1N?u`m@4!FrXN@*0eJ}M&>Rmw3WXh-qz4Zkh$nDF1G}pQAUl!kD<<*- z+oZvXEf|=F#erFRd)Q-NtLz?(h=>Taa;YyO2HAcSGA(EcK}&GjqyXMQTwtL9yfDls z;0Nr%!Ny)arvVPv{&#DV%|t{*_a8oFPtQUG2q(dLm(A^RgB(hE0J9|2ehG}~NW?Dt zumyFe%0UmHwh4pxa>P#hfR>%DV=vL~gHJLZ%io@=2mxMvb?ctJ5i_!LK&3nG)tyyd z?baOZ??V&y8g!Jw)l;igmojT%0+WWSLYqAXP!js{)z~vEq5in#jxd-{K0a_?A|h59 zC6tw8mTLC*Ee40;%^k~?^K^7|*?wOo;Fb+WbMf9K5bElNb4#C8Z{!2*m)b($`ax`w&sBu|Hij!( zTPX~tu7!Oc#}SH3g_$n6tEZe!-*meo4izPyaHwX)=^=2r6-4DQn%VyJ0Ye#7D*&zlL`?-W#0 znUc26GE$tj6OCZYqm*4a3Oole8ovrJU{15h4`4oUB;}Px<-Vc&jQnXa|&~z?T>g(O<1% zO|MmZW$xcW++F|P(6kF}XtGsef+JutTTb>Ndcn*b@$DNX4A<2*1GDL*>|b@(pW<#G z4CNq*G$5u;l<1?Al9Iwe&1tg})X;&a5-JPxP*8Ub2h%+L1T?tBpct2wl$2ZCjG|&YD$Df80Rx@IW5H+Ia-5FT$LOq{vx;Qy{lVZNEp%#OQKupHsKl|9?6DvhrTB|IrqPZeUG3c6g9Q39a#S?0TR}Y;!mZ1cf5=IWDNp1UUDB zNGWRCtg!VzD#=$eqzRHm4_s`WcO<`ErZC@V9loa2;1`A0J`X%mpd#6y~sgwK}#;m(`{u=F4^=zza7@) z_UP~G3IKr4vWIDGerwBFsSC^mcu0J&p}|mk&&p>TrO$yqIz7c2K)YUDevE-k&XS%g zEOhs1IVJcQEW-Db9*=@BgpT~5*l+fi~d^>;JP#UTj?2aRVg1L)nq$zi@rUS5%L}B zP|FQUMZGQn66E#%PxQ5WhnY2Ap1-X@7mM-MdxZ*^gwD*D1NkbN@hu1TfTL&Ft$pfc zL}ySJckJZ7^>9^#af+>SNT`f;vpTMpeXIReGd@jN`7~4b_SH5|0?jaGI*Zk=UcDZ$wunSeY!>=rIk`2+P)(7yz2u(ey(Cjs z>Ex`znU9xw8eJh4Nh6uq)!8WweEmT3Mj_^^y@Yje0895nnjuJ!Ptn=#6)IAXe3-kq z_A~P=<_yi5}8bc`Tb{yGj{rsj{TR6lT%<)OQEG9Zals zM@JhONuu`!JH`236gv0Ej~3czkk+vZ`NuIJ_snUzI|yPu^;uKvzV{nYuGcPXOBbel zFqO3a%qsp}Sk3}h+)LKdKp(PHdh?aXw|nW#m{_XM$-^NjWvVm08Kv}?ODAQfyrIJbL zPZkf+TlP~?);uk-ydkU-ciDOw_PMmbyRo=@h3uQc8B0Ri&tVjQH2zJF2O(b$gFiu} z2nWo0I=he_UcJ(QnKS-Tfs;)%+`9*3f1SkAut#?^Q4Tl#=8ex@gF(^<4gAy8=r~HOnCqSjrKyJQK$h7zL*rI?A2AUR= z4nWKCY50y9y1e73n!wvE*KF;92!yCmbJ$B+)AwbnxMq)76@wz~#wQe5lBk12=Fefx z;kjdyl{swHB(uyZJ_Yta9#{9tN()Ych2V2!l4u`PG1S?s5WeOb8#>h|G_4;SI40yQ zf4XlZyR@KMelOr*#@E2N%yJFPlE$UwAqxG22U*IgaGGgG)Oh2?y2xZQC&eRB_Sbo@ zE>bcc0tK+QK(Gl73;PLVcp6CEfI;)z+#KL0{&F1csviEUd2P5#7wzxDK@eq&WiWHs z1|Njb!71x(PI+u46%)?g@N{gWY8|#~KI12euuzAHcZ%2imYJgCXXGHAtYB)!ZEpKS#NG@6o- zv>=4>q;qBN%DmYsj=RqH36#RDZE75U>hJE;orc8g)hiJeo1}qoufXCJ z7n1($yZwfuYxyQ5-DsrIl6RN-0xAdZ`(v>c_31mKiL6b`cWPW@L>R1@940LcBnv| zJJPeGuWt=B4{?BSMDscW@;{V__?&MZB)#|cTNT>kS{vxN{6ArB#yRjhuV9Y%ccyxi zBchc_N9oU>^J2&lo3!qtx`EExWSTCDMK;2X08Gh-bd4Sw_w{%CGmq$3rxB-P5cOwe z3vVvorTl>HorBYH&H8e%P}SE){JP=V@c3(R61y>n3BKSrx|JF3edOZM*pQChoqQKF)vl*#(?wW}E&_Cr|Q+DEy^Y{Ly23T4@`u`2dZFh-AeXkjQHJ z0_dB--a!_}Q9-PG*tKY@XrOmrc7B}#f zqgc|fCu3n5TS=eml#Qc`k%|sVj_H|LE5X9CroQ!74w8F4BHDrq4+ki@B~VH+ef<}E z1WE?b)6---rq%|AKj+&oabo0o2uZ$b+13igW}Qb``UxE!9ZkV?0Bya6BOVl3T1b>_ z5v#kN$U(8s=12~k^(qRK(}O}mMlmz0+DytZ6lg;R$JKVpwAkVm&OQ%K(6R1#r&o}zM8cm^ZcBcvFfxzx6^=Cn{y*d>#vqXFtm91agC{a^V+ zn1OdCI~)btKGxsgKj{yeDL!R#0(W;7CAU7$B{KN)(TPmi9vSoo@`a@tzy@+SyP7)Y zCFnOs;ZSwMX%7X9Pqw4pY*MUwk3A|I2qcOF%&MS^Z&aj*C$03%O!n7>Q~Z%XpfvR# z^Uk0?uz&pObNiP#0@RFuZ3QlK!(XSK{$u?@2bV_i+ePwF1fKHm_}Ps2Y;C^t`Xv1K zO9Q-s-Xr?E6KmIzBYqxqCp@fm+-nhhD$1Dir0ZsBaNX9K=KX8YSFcB{H8P?>qm9L8 zlt{QkZ$_FGu+bIobcSQCkDo=*QgBDT>KMcrFAvP8RYce|uoc&4)0?kwbko`1Z!&|s zTV-~t4-b+`jrYWayW1hK8qjU4kCqtDBQ1NvVqolEy%Z`A&tVl&m?;hOUvCJI^O;sw zWUJU?=)dYUX|1=3Njv)Kw>9UV3P+~*TI@vKBL=}d)BU8Hau#@4OVk^8u*>pvOI`F8T%lR}(|dwMyMaet{0{=7x8>R^ca zvH&7h({@CM+qHIvRzYXMUp>_Crb0pkUwSm!x4H~hDsi%gacJ_k^!4+Pgxr_b zmzAO4UXqBdzI~^flp#@Z?>8>Z#!iF(+y!MVxX$O{Ahw&!jJMJH2@6nRV(#viWoxWp z?RaAdnzat<0KfU;BP?jVEOtE7T;_qxUvDffP`*|y6q&ah}RlQ9=E{_>=lym5_xW2 zf#Xluo6E8|HQaeARLNIG`zd>=6bA ze}mhN!EEh?Kn5)ZMI*3CqUP`a^&*3Oj9BzSpObE84rD*0q8<%1J)EdpMlZ3KWfQ&TP%RFnPm2} zcATrrp7-WX(N?;8HJ@HYMrXpdtO&(&7v$s5$ntGH_P$?MHfSdf8_E)4VRGS3*q_^C zao9knwOh}Z4>2Ck(iTjpOv92wHR#xM2c2Xp{F5dI}Bc{RnC}W~%$Qq~B4E3`p7eX9!+H9VTtBu@mZY z*rN4oWrGBMO=8N*tMa3u@`1Gy>RfL~=b&sIPUg)E#k`h2Zp>FO#1Ty6l_WPH9p~-6MRVBQO#JoSwaM3TiFe6D80VQth^2XbWuZ z-R%`l{Hy`v;@;jKV`UTQ6lgcstNswVhMVzkWko{pZ^}y5Vfk=%O3UvQ66Y9&Rm;Eg zZFN)lrbT$UhZMK=StUQ7V_Uq`(+hWpc?`z|HJr8vMvRG!`!W_gvqNb;H-AvGz57(S zv}D;%!CGzjg!J!Bg7C<{U|NQ9%{IsHCVxYRPjG+bn&VY=B z0lrt-%9^A_>lQ{Pff1c&FJ5?pGMz2Rc&hw0xl}@K2`=>A4i%hH0&~tKpaSd;D~NCU z-CPI>Sa1PN78XNaOg;n{^ZoL|(0lTA?$b}m`DJ(lB|Ctwqns+Tx+8#rpst-;_t^;! ztsBwfK=r`zsG81#U6l~ZXO2OB+Ele2?3(lK(hM2y%!AjkYv~_rG2rR#oSs-q%`iST zFm;DwZ$hVK(4zAVw6EZTzv7)%kA^y{H#F4n!21_$p&i+B)1VrJQj-Arwe{CI+kZwS zSUsN_8VZB;n3GercFd-Q&Y(TM#btfC30&vo90o+xt{WFYk*@g7-ovDGlQcE4d_kwpPAi9iY2d^C=h;~l z|IjI-;#`>&Eeoc3ow)G}--XSnw?g?Ml=U9>Y*dC&g z(%{uXYFAsaP!H+sT{9#(D3*2WZ*$K-2}dfV+Wfr$CA0B+)b3UBRWn9)_J>LNPe1g< z>{06vF;@s`=#2DVa2HwJ%+;jRAJevakAFU}f-Y4RIA}@rKVXfYWhuNMGf@+WL%JZ4 z3!sMmfL{Ib-85mK0kg}t#ki5_S&706T^Z2Pv6 zbkI4m6tn~s#0qw%f$LC1bt8Wdo-JQt-4@|L}hPLLifAyqLc{sspb2} zb&7X~5=U6>bUbMj-d;9fi17(@a2hlgp^ciQOHV0GNi*@G!VYcSz-Ja9>$))18lWKi zv6wE|fXp?fv@%%r2^9FPbEf$Jhm0D)k?71W@W`_41%%bmOS3H1@9u0LmPMb=Jr%5S zZ|2W_ok7~nn)d_3T7zs6r@s;ytG{dGXosjeC4{j%Fvq61mdUBM*$L##1+;_iKYD&+ zD!Nf6CvEKk8NW!hZKr-ZHD|Gv4JRAVmzBjnsiCD0j6wM;_v&ZwUTxB@(|ZwCI`T$< zg|nbY|CMy^mV>hLknAXu_5;W9g8|Y6lzrWaGiOu{*@(#FT4MF<@-(U5wb0O!q0D5Y zo(Am_YiwVTAAE87AOxk{P}Dr3p?VPEKH_(Dwe+h>va}#N(0JyV0d3xq$v1aN;J6dR zBOLpzQNQ$?5-r<~*N5**13`?L_QHL#k{JD(%A?har2SR2(Nvb?rRA4{L%1&weU~7_ z8dIH@U9^_zGj+xvmPp9BI~(d>F#g^R&!|81aX&rB5fikuQm~kr!_^4wz0)$ru5IU4 z?03I(V618S^Q<1g689=tRjt7qAN+BQQ2oHtV*#9mrjU>joLcBJs?*P|FP3%}D_*SN zNfbE3@DE=LrMn^ER3)|``tfX=-SPQV1%dO|;@EJJayRA+l)FJ+&NIIO^p{3kv{jf8 zWAkFVREPDGyv`2Pjj2nhg={AhuY4sRpU#&&F+Ngt=v4X#Bd2fcYvGkX3-$-nP?AST z$O%jbGzibN#qnV57e1Xys7_CR92#mJ^QuAD(s<`zxPtPH)1sQdJMcX;Le=or2$OZK z<84};)w1ua!)L+eDf*jWI%k11_w&UOvcK&!HZ!t4XKrScaUpHSr#`c9s^p;*-f`Di zx!FNxQay)f6A8=XYOY+7)|b0mg|#S`->0-1XM!wc%(%DNS92CZBK!&SsojubAvtkk z^ep6hW_Vj)S%T}D-psf`5f5FwnRF~>5?wem#OowdB zbC4AMy+aS~?O zj^V-hQoS_4BBl3QG9Wbd1~6X8Axa8iN0|xtjbzZub;M{_J^6;-*(Kzs-0)Ug;$+;e z=Ete=y)8Cqn%0HBtvQ@0n5WnTvL6Pl6JVe|{DBQ{=reL=eW%qI8vNj5i zsc6*GVINf661PZbI>2hxN^ZA3eG^CwpQ^bbV0ayqhy`>M9OPj+g&Kd_T9unaqESA) zke(rZJF@hVAYMkp%$IU>06}S4aG#w_#vvywRD1>cIqk!zuC&`yB zc#xa<@`apm?N3AvJny9aR}#f__~xW6gFGs`6Z_{vT$3x^WONXlbgRJe`Hd`GS@Y(b z7*870osYYs*XQpz5V{;&%RuDT#`s+QBf(cP)V3}yTM_A{XIXO<^tx2Ge#!TW09e#B z2=s|vzfR7ob1k9p;SP`JLC$AO&FM;y#PVq8)(vK!owZ^YniV8-uk}`;V-}RM$cg|Q zNE2~v^rjAno%v$L>N_*i?%I=vxDMmF_fX>_XQ{%8C_S}a@tKBH+ zX9kwfJszKR`S@My$cx*Q7a#bMZ@U(!ja-v8>V4_kS0h-)@{8IyeNJ7@*2tFn3?enY z$_^SfqlY#$ViSXuM?QMxm&j9(z%zo2J?q~(cT9XNJRF$^aw#88sztE7PMZGWSo!`U zYH6`@yCOMHzu`XC%qhPyhpg8W-*w~jVN{}EOO`^~KAYr*3$&yQ!a?|e1F!r`D@5J1 zFwLPyC|Wl(Lwt@a|1d4j*A@J_wF@Ek8%j(w2rIW8*n zUF5LpWFh9)k_HG~h*J2o9D>^CXCwQ^3)rt-a>TK; zw7ft3Dgw%R@Dfk=6;gv)Ajmk;agrRdeeUioxRto>IH8h++d?j0KR+^fpBp)+!#WD; z#3Wd9^r0yO=AWueze6GWbKcIS|SEuMs zyf>Vaue3$Q#T~t7VZn+6=eN|nynt$#E&fcf2p#L}?EIUh^&WhP@GJMhS=9awuR%UA zouU6(T~2>1AjSbZ8RT_&y`f^hRWSHlwjGI8f^FL$OgR{1@CE&TUKjrn!1Fn0LMMqr zH9`xAZNP|A%jyH@8E^(@%9M?}>bCP-@`qX7WO04n{@m3Fq5uk>px#{775Mx*%PsFU zZNQQ8?-M3M)PjF);&iL}dA=0=X?q7>0)MU|DWLnBS|gaSOHI@OpR(Mn2J?x7lT$HJ z{hG?*mats@A_Z|VTxjO$Lu@A<16f5WNy%D3ufY*jnI*aA^Y^xca4xi7AR#aPc1P0F zf{8S?ek(-dzj~HU?)p@@p77X<=$-?WnKC4 zy#k1k&zBwGTk?z7|}KEbzh7>qDfvQ`QB9JHPo(7Chg5&^LtElRPAYPcvzsv zu3MbV9!yv-{IEXNxiXQ5_TO?w_uKU<^aaxd`TO7dSgh~7v(~qP#qteo;2k)y`29N_ zq-?=I!EyKXLGZIJt*=i(h#bzWk#J{`xx4N_`&d(e%5~!|Am(lXa*d^W;}YEY$|i|f zSIXq@!2v0?CF{KB$jaif>@)B=#Ii9=&fsQ<)sQdhaM@5?LqLPuiN3{6hPEF3bAam<{e?tIad!FWwO~o;RV{oV?Uz zg&vN&*@v+@pCnW{JIUyX{%D7OVbpmE$E#=^jKr z8~%g>lrCZgo>3j18jKuuZg`=GI%p3fJNGalr1XJ63FZRpO+j;KPNwg37%&xlf3Om< z|K3%h3TMM6ko*Q1qYaRSRr76CqjFsEq5Dz~=?I6Z1bbeG#S5T|-kl$MSqY#%6YmW2f0e(o zD@$d#AyH|cPH$*~{J>1kBj7bRyZy1GQ*KT^zNcX?LHAHYX1$J$u-e%G!mkx?b6u}j zM22jq@feP{IM({7*^>xE?6Jd1M|u zreCV4lsq-jDa+@0BWLVNS~sI0H;0$YU|T%zmwY>3ckX*#q5mWd&9i~lVT*N}`kH&9 z>v^>H$k7YW)W|cvxq}M7U!>{u)waQMOcf?XHn4P`dp73X2nK2!{^_+DwVSdBu9XN7 zE(Vs4QJTIYPT$PR~;lrod$B$z7(Y+`<$9vI#pPa0qWNUPp{{xhnY^Ykk^? z+aAnlHPfq*h<_K)R}z$#_Yf0A?l=~y61{U@!|mo(k`exv^oz{27qfs(_lu3dlk8rX zUr6(9DmN^rqBnP1-VFgB&fc}X;bYbv#b3Sf|Efu0QxC?G|#j6557O z%(D3mY#2LV-%f3PMmF2OV{n0|DonH|aH8!%-GkO<{^^$L;2p}AT5T_ztA$+60tx~x z?kZ)P5sUx_O>Vr@c^*!D-~fFF{;x=8b%~#xNpKm0gM)ovAm%w2$mPV;5Fv)alPh$p zJflSh1v}$vC0CTxdg%pbwWC{J@X;r}39Js7>uxn3Dlw-EbMATLXMdg3nms#rPe88Z z5$2S+ZWfTit{`tS}^v$`6{|qw_j*x%#`DOj=0gQ zrvp7G!M*Jj=yj61L)*z}>U{g&4bdWGZ4hZrW8-bt9b#oTysV9-wd zkoVC|1=1hsM`uli@x811X$0aP?q``I!>GQ+Q{1>#!j3-Pa&v*;b02BR_}T@c%)gvz z9;DB+THTKz?h{Np<_^GQsgce1<@P5VYXN>bIPQ6*;#Kr0xBl}}C1hm@zUPYInP{rio+aWU^Z0{w)T)k`_(jBfc#I9FO89p<0JwZXooldJ7Y@QyNo7j@F zmPAb1_3%pkC*84Hk)3B`Gi*2S73cw7^H=9l z5I9Kxk3NZs+UrRNWJw!kVtu^@w#{BeonZERTRu3-Q%%}xp-b0RYTWHG_Jm$iPL7_P zJ#=rYX73)*LQK3bgA!MMS~(0?L_~z_uRFB>TkRpb4h6eF$nnP!R$KN6(8PiSGLzDY z=MY8lf11|+w6uw>AcXQ0Ztz81JRu0ZbV zjXxUXBvY~4o6|^j-dQj^0$Ys&oMmyt=$bT3x4zHZRMID zp~HXJYKI%Ngv;68gns585ft06|M*`rFy^}#_tJ_nw* z-MRamZaI(LQB$bUNIa*Yb{^f2=GQPj@6}t4uo?tZGxyO7;$|a;fLr{j*Qp2qwWEP- zaW2$5peF4yYzXyGS#7P*27KaH9`8c);jUJ5#1*k57<}Ef7~3oZ`q&e-x1mRj@VM7e zaPU-o;Q(;@M}uy*cV(*MBBdy6_ybigZVEj^hn(Vh|Loa0119fPYQgEsXTHhv6KAN~ z#-&>{7V5Gm5=$L&!WVHrtW3%qt!WToYL+kUJxd%leV~`Oer+M;{ba)_o6Tk80TheD z>#|kw$V-5U@yc`A!ZU%nWFUtj-Mr0D+XNzKfK4Z`rLC{Ftpz zjr{-EQNJRgf+|#<7Gj`C``BKWAZ+53#)uxa3)GcXdtpj_inXeo9m~i2V zi;FvBC!&xe!H`A$F&yYCdIGm45^RD?K;hM5mD|UqT}F2KjP@~Q&tC`%2yo5F@9#X| z!s~sEDnqtj!9X9ht&dg<`9*c200kO#lV{?~$v~y2CXdO=h8G?>JB*W?qbNB}okuqU zWizI1`N*EVB84B}&^YbnXFS}52eefSUUDV6mFF1JcRM_Xw2z@wSII>v`gvL?)Y;Bn zCw=95$5&MzyIv=B|GcAS6LpfqsT~XQ7h=4d299j5dVNvJ!+XDr=suzzrseKgajO!|yaKU$0?>837jSfq4T2i#v<{p~%x2HK& zh;N4(IPjdoZ+HTxG~^q=w3J|I8frOCoQAl=tvh$lA`L6`7xz=(;+#n^`~@G;Gx+!d zlAjyW{rs^aHq5c{)|>@rQ>cEefmiK`-0qDZNx@mdd&mfZ;AN(iUukkLUFR`T*K-Hw zo&RP;K_Kcb=Q*`< zi;Kj9i#Sd@4fX6lgMn+oVnca~NS!q`{{V$9Ug|0-zi1khNK+H@)k!n)Ui=S!-0^Q+ z?Lsn$n%X;p*E~^v>P14!eVSq^Mzya4U*+#a5lt@Bxfg5jR($jfiOY+SyU((~w5ZzX zO-N-RsX6ZP=}29XTM1DLzjF8DWLq2}&JYq3g6|k2G!_6x?*@nLtqzUrG6ob+*`~gK z`I|M{bWK8fSo>)(sMtvr#W8H`-l@()q8BI1(5JtUGcc>L*h32z_rJn{u#o--Jpl7>NsMVIYf&|mL^*Soe17mgYKcE9x>J*Rm znfdtx{ob<8oo?ofv$Hes!7d62#6d(p5&E(pKE6`_!?b~Ee*ZMs{{AJC9uH5hvO4f5 zwyt-)jBUZ>0Sa_X=^|}iiVEQh(RmRgUBKk^SJf?aar9mKXczV2KRFOe_bSv@Y|d-y zr1Q%97`ls1GpnEll^=Z~xo^k7TQK#G=To@B>>`oU;(|`vAjWIs1#jQMkcz%*T@?~} zUZW)UFmtQAm*#sU^WBG!^Ph=jnz2m6O-Rj(nsJ6}%it#lejq-lRR%cpzSd(evK*HX z6k>6ahs*yrZ|XU%iI@>{K`_ExSx~lRTMs)H^MS?#mwezAyYrg~JiZ z#K#73R!G5ksG*=-P^oWu;%yA;-2*IDtEV82lL-zuq(#2Ex{BWLijw=OrxjHQD|I8t zFzD1nKO8~YAcmCaHUnWu%b+(rq89w-IpjNI>ZN0Dbv%XE_hD##=P*>)V5PvK-#d>KiWB*Lc05N8+6%*+vFg1iM?86xDlk6PY%$)3& z=)cEfHJ|gF7lZi=5N}gNqi2?jNyT4|I$IZ^J(${H2o;D*=XlIC(%!DFulKzZ(Kz() z-;^C~k}EOlOczEF)}k~!%cl)T>)!{cRHE*^B>nn>QFs8}+bi4IM)*2E{>@GR?q?cq zZk2}St2W|&`<4PUH;8yZ>_I^k_T^-(DWqO;kpSCyzT0!}<0aV_>C-x!Z?RORXTPBS z*K6t2l|kFWa}xISX&ra~rDSCxs**c!XS7yoU8OiMRCE(KRIkaqRi~QlK*E4?}1)jlc91pq+^TR zuP|O?$fjGC=p3i-&enP^SvMADT>yp18KKAY9QOi28{{4fY^`_u@<7QFd#!I@K(8`rFEZ%bs(fEr#9}Fd<=)|BqUU{8nW7P z!y}kfb11#TfctPr{zIX5p&bM2(W6J!$uDZM03c+R)8xi z`AI4OT;jB6U2>jQ)qwFfc-b;!68M!fvTn#)%*J~7_1%Jxr;iPlTNu?7`jgbF9Fz_L z{Bdv#f#dWVN$^GhsMjF=p|&DoVJeCkJg)$ryaztectOY8y$*j43*Y9-T#10mB8dG{ zAx+}t_5n^+-#jQA&P2=XSBrLa9J^IjRmz2yrwS}*=}%}$ z!K)$!3m)7vUm>DM$!{ai61_YF8t>=#~@bSf9l3c->_L$#I0IlC%fdA zr|1#12y#z_4Vz)$9P=(wh{7Faauq{v5aB?=a5ieUZML#uJN5kP+htcE=3Cd5aSLfz zfksQu#`YA(dXSKlXPfZ3z^xi^j>`|J1zFFQ&*bDfjCve~2{Tb9Yy^ETZP_g@S83fo ziZp6Ke1{Px*8^+#H?5$F#aAGKtbQPmIRJuk1LPQ`Cx+lxg(i)4ud*s%wp?m3t7|*I|i9p z&L;o}O@zGZ0i^E*-xYOsuFPq<1~<1F^!s2bz4I5@rAwE}VXHI#kQejgC4*`8>sqME zZBk?$Ns-lrG{o|5!ot&Y{A(&K)8H}7$={odGdF;a5^w_e5x*@51dLCSkSNO?L|7|) zcHhpzi_2+vpQ~DU)J#^$d4p9pmQw*^-=H8mnE!~xu~#}oR$!=8?kVE%GR*FCYOmm6V(6F3=esq4U5=dB z;sU(T&#+@4tHW6$d@6@gT;(xbhshYjX#kr*Qf0DwYyKV-8qOP^eUPu5hJzC=U&b2z z0hY>3MKwcx?l7dYVW)w=n)y>-!>&wmfWD?YzPY=#pg`&cDHrS2X$3mj*c-rZ{Q2P3lB72D3LD34>oLQ6XO2)Vs;-dGpi!O>qDgMdI9gCC;W zWxyQ`HsUB)-BJ+)XDh&yl>IU6CL?GE*a4Z~N+93v%2J@2fIqLgfAa{QMtZs#&?EHg zG*TKUHBLj`i-}J zn@UwF6S$oM|iJdM}BOtW&fVoxnJkOn8|%a zmxcAd6!-hMPk&$?*Fj#0GRYj;T!2#2p0Y$NjlflczjY-+0@Gb&(wlRI#TuH!Heb6M zGRnd9NNmGT2`$m9%r}oHJOqt!tqUwSkfVVAt7-5U;A-@t37!w;lEUh-2vx1@u2N+_ zkE0iFJW$+wa9*q@RNcHP0vzNA zQRBcCheSipvK?S>^V9=L;M3~a_}~&DMJ@M z6HG`@*+RCw5#(70CZ-CVSH!{_h)4aM0mu5VJvFSSsF6JYlO@CI5-mdq_eVYC6;~=Q&WR&X4$-NtC=Qv5u)lP7N5lcy3-6b1`=+8Haw!_;J}UO3!4o> zLBvH|4*cYWt`GY&(Rtnw@GeuitSZ1BgEfhI0uBin z6!IC;9*F#gWGs;OD5@L5GeGZT5m-6MBrj0G>q+DUKX16g>@Eag0%sjd;9Vgs7Wj-d zR=eeLDT7alUA|JorQnMO`@Mxe07CpyLEkV_g(r_Rtusp|p0{(!1!4)^vpOOG63BpU z8NO{Fz{JR?0O)`Sgy5z?D*nXRS00L<*^TPFJQ?Gm@}hg1eq-AMWAHFCx`&2@Sak9- zX{jb8B+Q*v)zHX;OQjDhHmVyQT(l$XF7Q~w!j{P}H}Kqg({=ev%bCAs3vu*;lOEx^ z2fH%U@GD#3n19WPB84Ia5KXOYa7?OJTy?6lf}#x`>I^6#Tj3xQAGreQ5eAsJ1@EL4 zHnr2&fNvm|F?$*uyqiS6PNr~CH#RqKtEhMb4G9WBJ$T5176k0RP4~zlpzDe0&NQU^ z&WwR<64b6wwyhd9%sRvVqd4X&{Ky;RLOA@q62;~v5Vx~Ij6c_OD~||0BO1r z5DYls+PFxj1%6;AwcGw%|4FFC;Qj^p%fg`%)gBpucsG?p@dd&XOc2w{;39-4(ALH~ z?-|@oxAvM>?gQ8y_6=6s8KtIjAaiK24!4BS^SNwt0@ONa4bEstO$729{3}oh*lR~!q^p5sh5hSzq66bA}pPUHvxE!{DISxf=z zdSlS=Akv@)vjDP%spO+4?o2{Z8OI0?8~~sI?+To;L}C1ytE($K0Z$DR9lhcAgu~5H z1k|8Uz{$CZscfQp7yt)rR&XC3r{sSF_a1N%rJlQ*!)J_)N<)ZY5O2Bn`L)-XIU-~B z7=%v)G$bYj(2VonkwpsIB(hrvHO1HdA{uyT48T4WbjRz&07mi3EEd6q94Wi7?_&Qyw@zgL{m)}9 ha{B%EzB|8%>uBCq9``QHBd9LF4vG1q<1eOx_quE7H!{>58C; zu%OtbGk4wG5J*WOA;<441f5-Ng;d{g>4Li)LBNfW5JYda|Dwo-y|#lO)>}$9uIb)S zTpIIL)gzKSREN>2$T|uj2Ra7-6Gd z3AmfMO2y=>F$eBlD&f%^;nCA6jeTnv6P1A`;O2{%&t(X&ngk_JPf&7k89)N_e`9ToR;bTza z0SZbe_KX|^F&;P!S>6iYfF?x6#j~&2c3O$r%q#&<6{)Rf!q3= zR#a4!!s!HIEB|-z-u3tPy7sM5QBgg+aZZE{Izv7$EoXt=h$=Lz$=cc3iS1ZhTN~)> zL-wttX~KOPVAU&h;tgs$&N+`tt@gAq9lT#s&dSdqY_;_rG zx3~An!v~xs$MGBQ@EbfRT1f7h$|i^A&6`h{1dKD=+uP@?A3b_xfA5~Iot<5J3LPYT z^SsUZ$MNy31tt~hu$?LTvfG^ubz8Fu3wV4V#&>t^wloK1Nvo{v2hJ>GkG$-Q+88hZ zkC(CRySFWgm~2#YR)wGt3r<{ODd*>#VelJ14HMvt8#!nKTUNIov=GF6nb{%B2j{+( z)E}aNRFC~l-T(g=@fgwjy~#^YKSw}UY+ z^-_EOKQq#*H&cn`0A=T9KjbGG z1{NhrducaWY627w>S)Nk>U*t0@4eXA=yxs*-gO9q`yQd!R8k6JWo31nY@`^#V)IH% zb?9L`#e$}l!e71t5%d=iiW`!nQNHhYk)MB~G=;2slvz;M%d2X4m)L;c*;+#_*Absc z*O!;;Pa(vs-QC^K|8W7ShN`5r)P0Xk%&V(I|3)@1GB7U^`(zD4+N!<2^mCuvf*0oI zG_PH|R+2&k2|wYMmczjIYU2|U+!y-!$ZIKk{nMea!XQT8g&^K!___`S)L#79_bB1L zP(weXhIASd*KIfa)($n77T7;LoNL#Yb)J+1+BLRA0+%0Hsm09@HnCj6X>B@BAaM40 z?G!Q-bbWn&M{&3B+~Kie;FcF>kH+BGJYWt@KL^k7UFvz^>WddIewO7OU_LokkM+b1rG$) z_hYfIKYzXj27=>nWRnV~0TbuCS4$%m_}`~ms<#O>fc9n6VdoA)aEpk~GHE3x+JMI8 z3CQmG4`LJj0C@Q)`Ss!9<38JtGdP^X@_3zbjmJ`w+EED3c7%LN)7JJi3Wd_u*Jna^ zEfe!HGj9k82*@X25f)B`b2F4uK)n{%srvi+xRl;uFri-3Fc_?QIpKQR%N-wIH~veP zRKLI>zY{jQf|bL=#$cq(4Gs+0$S^>bC%8rB9?Hpu_m7OQt=)Hac6OT(^Qtr7dQczx z3-ofAfi)G-)ppNJsAv&pRXzSh#xQctLql$878 zkjTuJFL&ERP7T+3mHO;$PvGmf2|8L@Vdh>lCl5ZlR$y9nISfe!wO4{O{_@*#8PZ%v zPpE^vJ+~5mus}y%{*n3pse>CE8+I*Eev$Out>r|`o#hZmSl)0@0h?qF4x_A8($mu$ z#eoy&wF+;w6wzk8bdv^xEA5Z?e^>s$=zza2I!;Wn1{(!4IA4)vkT6zLpeW~$p#JwV z;;)zgRcrh%j!WD)CI+VQ>Na`M8k#nKhBkT{78iGlC_yHZm0}N6FwzCitZh9R!+dAs z?*ipN-TC{XeH8^S}+cdd-{<`BwbU}e1QC4 zyj2wx0;+3jGDd*@Al!vRa-^VbwZj1Ex%v6EGa`VfAIe#_%I~99+viY!e}86et@MW^ zDFZe!r~WD=?um?trKMaLocj(Hl-cl@Iy*i6x^n}$oRy7jBM`Q8?Zbx;;7LJvUjYe)8EQo$!T_v$R0CUWw|*y zK|bt3H=Z7YLa3B{*}g7*Dve4=$ou;B>sg}rpO_ElOciR_(Z+Qr>3p9dtz?19U}mBA z(GPAO9t%TntlxEZYN@NgD8Kh9eIU<(|JdQ|j0}09+TZ;Nbwu;1m>6C+1k^ahnB3=|Wy|_U+qR!=0o(RQ6!Yl}zw#h`{32M!}R7!2n@9 zC_j3EA?UYdqDd%4W@2t`ZY3tCs7RxkJ1F7@ICUPQ3v}K>q6ht{eo(sqxB7q6PC<|N zl$@Xn11+uNM2R%b3r8ZjyFnjJ%LYajbchlB{-v1y+pqX15jSbV*4dm6IPKYX;^N|B zCFYb`TwI(>O3SUxc>#91_qerRYEqcBD}o3jH_H<4G$0B zdNIGeY~b!*mZhGQ>rJRq%rhv`2aI|>@DLP&b~%_`Rb@0VFktWKH~;{V2|l&oTAcxK z2)63zRn}A-^{Qg<@yf#Sv#_r=L7IG&3_ZKi89C zT&{k~V-V z_x`ojsEu6U9nw3x62vsF-09L(QF;F|#rlWNJ5GHUfzV74a~^y|FPjZOsuB*SPh?n_ zOW%n0AC}_E7u=D6>wx8Y3W|#nnOs0ay*y5xU0rR=tDg7~z-Rfc-=Cw#T``3o622NT z$E+phIGjn|CgMM)$pc@7T3?Ynlge*UI0poui08Gsx;mgW<$VN;u>3_>sc;b>y9`Y| z<+>#thuPwj7EzSvWo`XgEZ>OJ&iCQ%uC@`-x24?G`kPy~lcQxiQEf~+I{|V@sFT*Zfk_=Z+ zc(ra~7^$FO#rF-}Ws^VGN&oP!H++wuWXb6<{v;V?P!?_YiS=bA6(z)S_P=)v_Y;xb zsHbcS=Z=G;z>B=(9vd5TNnt#EAYAy!OZM05NuWaoOv+o)>hkjPqqvZAg!rWtjM$>j z&oaTKo6oe|0n#fmahGkB8F(nP75`Mr;jOnsv>`d=bN~HDR7*Ia>Gy!%fl59>bKZ*K zj5{z)6e_i?Vlc2$q-)Q{)Wmm=5{`h?PN76tY|l z=9k+aFNKBr4i0&;q&Y6LI+Wh~7$E}-3yUrnjPzQ_KPKB?feGUu>+x!bsp;6CZdInG zT>~T_iCWK&7Bpi;?-bS$w9g!acRdC`bW?;;0rMK3nV6Uu+cDvV5agv|bfdw;&^I0QWPzINh#@cXq7DKHpmGeSc)C+>>vMHbqH&6R1?N*nXQ;9wTL z?55>!7)F|ao9lz7VA5Ru4Cxsd;9G+jN$Y(Y)|?Z?R`Tl;N0}}GAM_BMQPztWbRXib z;Ic3}!1>3=$Io>De;p7Iz{PPCIQNhXatT)*dw0p(?m+pfrO1+_JE9{a;o-w0BZ0Ip zvG^z~o}-fm%%)3)kOXdhu@qyENtUsT$$Kcr3FZJTowm zt$nMxv|l(4>^)^AFAEPfDal+jc47>EgeuN={{iTnn12=ct}trgqg6#ptA`rD!QlNvM3mBO{#C=`O= ze*3vl6=YV4XhI!;ld0W_5*Yxd`>q`QM{R&84aeZF#DC<(PDvKF zxSIyzE9tPWn%xoI^UVQAfjNm6w%XiIRLT(VtGEmZ>W{*0KB#vgQ*N{Vc#)9>b;E@3 zh_yCIu^_*dhx@}nBnJXgAB?0<{DyJpt!H=y$M;Lxd)?txVrLSSZLo(uiOR3Mr1n)xgY%KX=+46auCBgyolyof-^SiIF;TRzV6T=WsYe_| zhUyoY7mSaaX9Pt|kC+B3a(aEq!piIEMfJ4GvoTVjh-035IyxEE)spDlE!;&xL4A-g zbSKL=$P8zDPd=pX9~MYa1?i9C^82;WU<8F^*Chsc^;I{U`;>!J~FCwN9FT;ZNG3^-Tf?)I``=oYbIZ;87q zI+`g@B!ZBDZIZzG>`b4o*&lBn^5~;{zSM3r?@n^apmaeS_jK^6#-^5(TrPY2mPP%} zG^pD?24%dTp3ca*7a19u4fq%&IC`F*75nNu@U)L1kR+M_ zMH}~dfQ;d``wiQH-EI$l_Kc>$xJ(&T5yV9woqg8W^z`*}U%gUb_1*2dPhgFT_UC@`(?5x30Nmxy=?WEKdIUz~;&GFv>*a&&Yg zO+KQhef>OYm7;ksFF!wI*L$it;36MiPgmTPjdAbg`T5r=R}*P-ESHAMdVGZpi{(J_ z)t@MV+;>Da@1swtN3(;jlyv#rTDd7PS3v8@arNHNF*4Er;89)BHDE~&a2vqioLUkI zj9i`YfB)gb0HA(n6tjx6a}ni3zaHJ3vr;?vGN^uhNq z-kENH-n~q$$;#rv?(>PDS@j8-EMUc@&L?}##=YH!*~ycMDz0GYKIKGit=bTSEq0pG zIH?I2&oTEH@12znGtgOMAC(X_cm!$PuEK3zJ0>Dx8hk|!aol^X$d~NEOc&@#y?1Dr soeFBa@otayF!VC{fB!$`Z>Q}Zbtn0C`lY0?RS5hjDX8Blyl(0LKNOY=6aWAK literal 0 HcmV?d00001 diff --git a/labworks/LW3/images/5.png b/labworks/LW3/images/5.png new file mode 100644 index 0000000000000000000000000000000000000000..b89860dcb7da822a9ee6259c4ad58275b355bfc7 GIT binary patch literal 6711 zcmdT}cTkhr+J8X=R1{H~B1J_-EP#qg3811Fl-|35NRwVdOUQ~8VKuubQUn1By+j10 zND*llqzgp4G@}F(1B6II;GVcw@7=lEzMcEe$ILsK$()?`l;_tT?&|4iZr{3hD+EE? z;a4;aAc!p;JgMBA;2Wd99BJ^OFMJnbFJi{5twC**A;VL2;#M4J#4vZIW7>iClju5 z-Y76-VJz&LF^$@chuQa;_oiWZuw*V^IW3%3zst%x3UWt zTAsU(J?g2x;X=Rn^Lmz>Nx6Jda&l*reZ#GbB1J8U{u!-b=M%AmLD2QU1L_d8n}Zv=ej8$guI-e7 z&|BC!AldV12s+HY6MEGoMP#chz~OWgWNb}bUGr7MFw}DpT1t`7KQxq=lCtlfu-s>) z&g;z|7iZtJcXpPGZGt}kWMN@(#(S!Xt>VZi=DmTTVUZ>THN9f4t70tC0i@BqqlVee z9f@+%Qc^uawxJaDR*HiHB)peIqXk*9FH>5@3u!GG5CW7nL6&3i|nVHJ=_I8Gt2oGnfq+o2b{h`&ZoZ+-JhUy1|x`O9; zf6{3uBO@bz)UBpyK51!b18eIsYX)t3S&Dz_rQ^`69-$=&xzwpJx3FMrVq(%XZEkMv z>gM*+ZKJ(iYn8eFc}mm^l2u8p-&Xwe>4k>tvNd3Pg_`V;3cK6}8GY*1sWUz^SIR3Y zG*!mO$BWe^yzuKbI8z&(!k_~L?Xv11qYVrU&LBuu#-^rG;zT0R(BHp&>$YtUOg{)M zDUhIhK}tpjKV0rc4HsWiUm|qlL&&u`#l!@xTK#aff5GtZ z@Nz8~sjG<*t0mss0--10fNLGRIC_+SYa5wniD82RuQXiOQ%&=HweW#_dlST?`v;fI z!Nv|HO8iMB{689WSATHRD;qexE&cvTxtnQ!>$Rj)j(Xh@O*AUrRukFrl3XW3l`}Rr z))xnK4Yf8Y8&`Hn zBj)O!%lGzXsY~p{cy5P;4@@oY?P-n`ihuARGtV$*u35;|$k%rX%~<(WkqPkgJ9j^U zDFrX*1}qF`WoI9T(MEme=I7@T-%1T2=pOY7gy!I1g5n=Nn#)mR=6&c$%AA_AXHs!t z#+sT@s;e^(P&8a_uAZzg5AM;UM`jof=!&{`7((5`BKZl5?jnEY%<{`IBDI}JZ3*Fl z)NkKqgmL*T49m-(Ju9uOtURu}8M<;nj<<)1t1liNwm>qecsfCCBX9Oig4@hLezqvR zsa=@175b^ke*IwO)r6BSoyqdm!PNZ2*Amm6(vT)cbf5I!*|OW7X$0!`gLjuAaX*QF zYs3tVQPe7IlAN5(>Az3>cuadvs`xq5D4D6b1K55ZzQhK z&!*%(b?4D>^QVBZgH*&smHedaU;64;R(Kc(1iWauFIw>Q=>hASKsl2ob|^ABcT@ks zKo%h0h0&_gi3R0=`5p$j9+#glovP%og@LUk#>B?1noC0x7y3OfNS!!g?Be25Ka%1b zOs=IZKb}~-45}tx68U8^3Q%)j#>J?zVCr1dV?jvvM$@u+8XM7NHNj5Lnay#YudEd9dtZ=u=Q*`qtT zbE~VB*36{%`v6>x%*=$}nC&lmwhh3IFbkdpR zFkH@)V6C8_pkQKA#Y2F0$2X6feLNubxL76i9No0RZ89}G*QcYI@eK zW>;5Nm!X)!{(gQRhn&&|dNVcUZ+0ZU)7}nU2^J%yl!{I1WawQ%)lUTTNKBT!cySro zp^mFP9Fw1)pNko)^mf>H_`C{7ctc2CvFG~9bI_~L8sDz=k4ogbi2r+#{)Q4K#EZjX zCFdNz+;HQOA7%SZ+5h)1en&P`x)hyYO{o_$ep*A-Q-#&7%2~_4_B2d5uXVaajBU%| zZ%9}Edyr%q5A=-+yT-^|41AeauqZ$Oxfoj`g!r2>h4Jk&=k?Cflaj2T@Pu)Geq~{4 znW_3gA1VB4oyp+xA5E5bvsc*?nR#7SDy>`LeZZffhjCS=Rua>?y98j{US0;e9v!Wu zZf$Md-rbGwN>%0>&B0nOLG2;7baO*S-`R^ z{DyW=G4DxE)VYC4H6S;ZK+1Z{T;8(YaVb`CtUT<}rHJ-7ZyIf*F6=+R0X3?RPDH}| z=ZqY0+{n$y$e36F=0!D4<|_&-xjyz~U1f3q^U~7kuYA7?%wBB$QqWuBZGS)3m(X<- z2DAS3>C@})_!Ri3&;dP~dY+SLz_lU0$`fF~T3&Os7YmqgRw=I9b5glxFOm2%G0|zb>^_Pe7DC_oyJ(Qxh#yryHBuW=LFJZf&apW7vp3g&n%_S~0m~tO z9rV8O$`8sM>}*6nP9tMuM;QA~!~YSogtK?e+eUGVVOoPZB&5H2y1zU5_XU4-d-|Jm zpFcMM)Mf~r{i)NZ%Wn;x8o=W<=iiQv6+M4`>Ylio4MuIfl69?sP!o3m!a{)`f#P#? zbW{pj#NHQG&ITglLYZm?48E0I>i9+wN&l3iFo4EEee13Hyn{!s9@Ls0^g^v179|M&mIB1;n$1 zY*5@k(l;5Im}GAgI_bQz&g7L>2Y9*Na6PcRtW2e!wh5Aq(hpa3ew(eW3dL6SzR_QHb80InM`;Oq;ks>~xIB1)2kAz4Wce=gQaYC~vqpC=o&w6(X_7f;g| z@&WT^t4vhwV*4>^85z^y;ObD-G@FnGc>zJexhS;7S8a+)zD2Igwpr_iiv+6Dc@s;yWu>e)>m0sg_NB({A@1)aTzxMU-XQ2NLUVcXle+{bN8T53ko}**dht9`2{ryIc zH*dNQJ$KB<;V|zAtAw;Siu{osi1+`AHoYJcJ*K^dFE z;^N|H=3tR!&fwtS=iw3u&1+GdkYv4n?|kU;$KGfhZGMO)BdLnMmqGRNsHu94p4-g+ z!@FzTkZ_#XoP0XaHnS& zz)gK(xXk6j{e6m0cOTJlo@%;F8?8uBSC8xO=}C8an>|+kOQ6|t69k%FvC;rawJXDJ zN`ar#U0q!tCL|yx9DwW|fwy;ciS?r)bjHzq2vn5|dAwFB^vg5QgcukcJPcoCF!w44 z6z&xfDMyfPm|t4e2ES0I{ecR(4?VvGPOU#h(RXT*7lN)B^wy9v*-%{-Av6y{if?CU zr^n>$h?6kbSWvBv0+Q}WYZ37rr4i5wue4oe*fn1 z^Q)nCY!yr9UVq$f`E^16rK}JTw{ZyN@af^%z8;u*TvVhTi8I?MREX;!S#>7CIU(A-{>OQ!TJu;Rz^JE zfGrdPfv~^`Adcvy^u!&y3Y_{uOl#)Fs2!JXA-Y_MgGHc91_7`@dcejC$qe&|XwsB< zWonoEtnr#~_}$KD-UjC8c|l7bj>^j$CnY6WyttJ#M|LSFVZQ796GNr2>fV(`0XcHzBE%&RdFa*fgo7#jb=ePnqy!B$#L&9=F@x!Pwo zhU$zNJ>9L6$pSK+F|pwRGZ^*v_dg0oC?iPo2nG<=<#h(RAU|I#M<=z<0RzhhJpg|M zLTw5@O+*pS#{u7YpcsQ>tiWDxna2HJCHb}2+`EvUmL%ZdFk&mkfT^-OLxHSzC8~wh z9XobxTiDph2oV@ED?nP4MwoH11uGP)jw+ljSp^buWIc&U^!-8o6?2j|j9YE6w|5d; z<4A>PTEiVo3!*#Rx2wqd<=_eH>i!#I;E=w_K51oRB~ud#dhBpK~7UXyp)sVkS26yHVj9Rz(mAoNO&ZMUpy0`(OY z6_b_x^KC*Ym*f=`EHO9o^YY;C?(Tf}sIRHA;aQC;iye}Z^7fp*={((XkL6^kSG)yy zI1j;rXN|*x$v*-{<-<32B%PLb>BH_v!a`{(p~U|p$T9mGwnL*)Kcnyp6QP-a9f1Y9 zr1B&_J}Yd4F>%>&ND6c_pTI)SIJEG9FyzWuSqLUo5&R}!ZwA1!z&Jf+{ax^QUm4iczjOhV+FT{+nYfyd4wIoU)0iy z>Fet|up-)yzZeGYAGK1N=CU}`#scE%5`p^0cHMwVrP9Ht{W*8+9p0Vmwjh;%=?4B^ zA0+I?((D)C z^JBIa4|sDh@PPw8J=b9|NuD^iV$4hJR3+m*d-hyhq`&(Y)px6Hs7&E2fN>tH2{IHF z73E{_4iN3qmwM7}-)4tv=17|6*GrCe0m=~Q?CHZ+A1~ef)%?%V>oTGbn0S(b+sl|P9wc?tZn&<_PTn0Y& zW*#h#qSJ#x`S9iuCsBk9H9}YF18h^ZSmDHGio^OFm#Kx0^IYu|Hoci)a9;&D;5AwWQn&$z@Xqt+^wk@T`- z$B+8~PZ??0I?n96c=2L517sE*K4Z($#jJ2iiRP4(^ z(8W&mt(b^m4qAFv0gFwb29G_x6l;Y<)-LpTd*PP6m~{UNkn$AlUURVgKg%Ulc#Ku= zr-k*=8H9wH0P?u#IHBd92no=Gzpe`94mgn%U^S}14$DQ9c90Na$&Vki)@u!{?^1BB z2YvYy>7K&4SHtz5fY0RjcsU5VCb{OO4qU+9-~PA8AL%Tm-mg{lP*^Cj3Ic!dOFA0G I7p~v_C(Nmx-2eap literal 0 HcmV?d00001 diff --git a/labworks/LW3/images/6.png b/labworks/LW3/images/6.png new file mode 100644 index 0000000000000000000000000000000000000000..e23252376d26b2cd9583f997bca8e4281d57dc7b GIT binary patch literal 123991 zcmbT7cTiJb*Y8yX1Stj(q)X^X@4Z*)pa{}Lq!S>7&;u$}s)*8iN9nyIHS`)G5PFc% zdxyZ~z4v|IdF~(2o!{Jmnf#vS6|>LSD|z|Skj z{oLNe!wn+I#|QeK5xlPMc6?fu%&+dALg1!u0=ajO)at*^`$ckv4)^ZgyQiV7@X9-F z8|&rqVa8|SaXb5K-mI^mRC6I|8Dm`pY0E?st3=ft->S;g`)gRuog8=ur-f~<;_WRj zxy<_8>g>l43twDR7ugt6+L#K)KhXFhp_{RhF(#DW{7F?zkg&*%9Ts?xc**B9nZ!WE zm!nOt%w(JDHMCRqY8#^S=V%)qfflD!(Wm&|$9IzVi`&F{|K|tAUsuMB9n!h}D&zNCR%l zo~jbsR_%ea`(QfFe1kY1)4FibA`K!C}#-la8rYwV`5g)DXaR=I|htN-8TO#IiJTx0Ht@V?V}n4U8q z4-nW2liAPUh{~!%j~T~+F3zdhLtKkQveLYlQ}s+0o^F1+VX~$#t_cgw3fucyH|f5w zF;q}^;#jLQSO}s7zyQO0TxXY_hhcy&vjpmQyXn$^zf0J~DxId$H0bgo=L<_E(U=Aw0#TcLG0(69TY znu(F1Rb`%{RD?|-UGb`a}?Xk0y$r=OIiU8KB$wn;}d3fH3}w)|gz zt&44`xsOd=AD(T--YziGZk@~BW-bObX;Z*BT{_+{q=<%y_eL)*S3F$; zoBvFKyg%qZM!#GrzdeYmm|; z3)dxQ4li#tN>3eUEsujE8UoqooMv`UWbO4(+e<;t-5@A2 zDb3VV2H~lNY7Mde#Oe4!3YPZEthmE{|AURsKLkDHS@K~1BC_`TT;+c)vX0c2{~Tm> zpw&})yN7oJ?>@KSOi6gSxVNjbKfzka8kJGq7&OSmTbdLe`u;w=ysYd2VkWAQq?#0R znTV8!%H{F+AGWCd8;gXMl<*4&k4?LmX+C{a(BT|ulJbxvQH-|jclo~nx$K0IFe-ETIx-} z*pm)9iuF%f$REd9pHRyKFXZga*4|!brgS|0?pgsS z&<~GRZ)OI@MeFY0hfQ)lp48(l&~u5aI>6-5cdf$$8m_r^zkpViscuyi*y#EA#aU;ctaO0ljI(h z538N?yb`sd&HdP3nr|t-67HDYgkyQ%0Chw)5Sae@8Or9GAJV$ml(HA=qvU!|6#IEO z%zI>S7sU<)D!dDzZJ_p6i9>8Yc{2H|y_r$uc+q#ouNM=W?)zY~tW373dfprBjMs20 zV9rM#kkoR+3_4c3{F}_87BGL!x^(;)p4GO0h+EWks8U4L3#KcLANsHt6JSj*0IQ}y zKh_ox{CFDV`epW$g#5XG+hqA*O#RJZH2Rk3JmVZMZQ>1W+fXIp7NJJ&+Ao&KL$cK) zpX=JJzvy$lLd)_3_5%i2@cljVO#)b2VC5>Kx4FU8cj=p+pjUVbpMU=4vUaYqnu{#6 zCb~8qGyGSi_|#_qryORMsHT+THayF4QN&bjPnn{wMNg~y)HpAhzJ-q08WpqC@KJPg zNl*oH8pNiZJL6~tisu-E_^>@fr2nBgzfk>LCa5IzmTorEFo^*fGr4ae9+}cEJZ#Kg zgIoBF0-!PJta22&UTI&a7l;`vF{q5aq2#l|D|QysHgUEq(s4aMTZ>$M>|*M^@KY_w z|4~c`{JGVHP_df0wb~!m^fDD$Qh0Vs%M)|l6sWSYyNEQ&WTM`SmJnN`!Eat2uGWkD z@8?FpCoLp}7eo`{n5izI?dV8jouu+W{DtLTKej%UwqYH9WD{4G607$8-NP@%*ytI% zrNsg{C!s!kpMKmILVFZd^ZRe*tu2^@!=}I5?h!JJ3XN@>m(18k`+ug2f!UX6hzbw9 zIe3#)eJ`2Ip2T@&R(j!028yeneS*Mm;7>(gE?|sX+r&?Wd5>M|ek=9$pJ`dX-OVAt z_h_GaHsaGxvdcqdLlY^lRJD)iXOXyt9(n z=`JN^@hRPh-g|oH%5v*N(mL!kG0TlSz?BB!+~*ev=UJC&=Edh*i}AL6ImwLl8GoI- zwi2$mlBza*H;&mXgQjEKwZ-f-a-67!AN?3uhIP769<#kl7}OgbvhKb=D*4BLrPVch z^Cnxtn%*jW`b2d8MV>)JA#-a(lyIvHs~KkI+-fpw%US$3J=o;AB>`6D9~44niDQW9 zuG;QBivDWgL~CQE1nIsymE*G`*%46s!1C5v%TBbO9i#|i%9U#J1T&HzblDlAQDkD& zt5II!v&)r5+I=$gVWcMLv9?-KdZ}TrO0|N;j|U?*vMsRkN|M-`RBftO=E@M?R!Uat zEZ;XQFVzFf;sdix;LyHMACv?^fY2iz-OksAqL zvaW&-hobs{;SzR1DO|-@%5M%xkhIs2Jry@kZJ!voJ)DYA6?2~{v^_|T9u4FD8(ksO zndEmn06BqVQUJif(@$>g1)ljA2=vElGLB`Wajv>(NdHhind2M=LzU%H%Nf7MVZFQNla;VoF-bu2xp6(Z(v!_q?<`A8{`in2=i); z+H;sXxXBm(IDKFcBb~RJuW8WW=Mfk;@Se<%t-WpN_v|(IuXfHf@@`Cx&C$A|YgXmf z^~F)IWZOyWo}xL&JKEFZEUMais`9{OZi}uL9tSCD>0(pKg;2L%Vn4)T+L`JZ8xEF$ zU=AT_LAb|?^fJxzQ%!{nmh~LVhI#;BiLDO5;&feoxz6_=>gn~M(EnYR-&Nc6YK+4F zU9zj(<+)_Z)iPLj0PyLaL{kS z-CA7h$Des@0P%`y9RSY$&fheK2(*|}QdM!Z>pq5-J@3Xe`r;(U*-gec;a$AiLbmPD z(D)CE5Ur9E0*GLO_X>yPflSQR^bm0*p0%C9 zjtu2Z?gHT_ZcIv2zF33!R(s(iF0LPe*r{FnpRdPj$SI+gkQ%BWGu7PCc$Pdme;Cic z)6>liGARO2ZBg6D_-x;p(xaSY%bAy7kfgG`-*-r+6&tK_jiH{aQ>uK^#g7x~nWGWU ziCi=8sJ1u$KoH&kZ0qYx>hLmw4=mJb8eN&9l!R>1wMyE#H=3%Yh+MH}nD)7Hp$lU? zJ1~=yic~d9?1Gc^CW^0tf>(4r}i0SJT*fXKi?tOq}-{e3HhTD1snNaUlwQ71ZLlGUDC42o z;#RiDW8Cif*k*nOyxi2t7bjg#@R~_fhsim$wK|L4qRk1jSxM_o9 z!9OCa*>YkbCt97leWm&A=XskM&QIy)~T3Uho|`s zcUinFW5G+kW)c_c?@Iv3__9B_AsI4QLBthFP8||R8kWcbwTs2054;=zJ~#J#S;5ys z@X2ob%{zS<5zY1RULX)?vHFth?MX3#gHLgEnwFwHi`ee#yc^LIH2?Exe?_5Z48*b0 z630w~D^C=zTa;u&wBC{E;d^a=Z0h?ILr18Nl`Me7Vy#~6W$%mo%5b)PUHCNE9D0^y zxBmBX&0Bc4#VNL-_($dSbwAh}v`dy@8136BVbq1)(nTk&Pan|GLe^PMh)L2Y00+^+ zBkP2(A0VhARzrM;jr-5le@5Jl93DSx<6VE_bMDe2N4?%z*{ZKH8XB%%77n}n=b1sh zOi!@CoAb72f|IZP#46P~Dxz)5d9lg$&r5XWWx(@1exxS)S%a8N$eFc}kaufZ(r?+@ z&hgx}m$MBdiL>eW!?QqN8d~8s)#_CO_u&J+0)cw%D+yJr7;Dl6(i3hU{S@uV+;PX{ z173>#fMH&JdjTIYYm!ZELR8-4Mkg!OiF1ROwvX-l(TnW%e_$x2Z5`To|GFgyfUOZ< z>7S{BmNOJ4<@8P8e!R@L9#w>mI$7YH%+WcbGbAr55TtF(!@ZJqQM;dguTInTVxzM~ zApw-t(m!7#wDImc?$Ay9i)!k(DSA=XChrLDo+0_yf+&uP(xoI_9mQxpihjPy0M3jt ziKgV4ZY#nv!_^}WrQfEdS1{2swf$shIzndic|Iw1c|2U}Qt64LAeE9nlNr|B5zh-` zXM8E&_E|OQt3#Z^FeIUhB4Rl5yeSN{P*Fj$-oU<*Iup|ge!#HvhT>ac&{}Q148+*Y zfi*+P*JqQ&Dt>lky?pI}z;ykpsz2}^MD@Qz^mZNtLSrDx_9>erK zHv8dkxQM^p$Cg@j(cPEbTlwW5J4pQ!2n5*3^Z+cZCpJ#}B0W$oH!ZWAd@C~Z7`a=Y zqQn84BHHiPM)@rjs*^+R{Fkl6)38H`d)X5kIFiJNmMn(W&b30X#AwHJVf*A|O@Z4PY+LHS!%ci0pNd6DS|rr4VlS8#ad1kM#o$vD9zX<$ z)8v#U%}ACHjEN0XNqIfM(U;567zv>m>tq4~MKayVfZLYyH*^Sv&3g#_@I^84PZwCF zRBd^ZjWUOkUE6S2KRe7`NN0>4l_$Z*<7{Jvl|C$Y&v3yj^Rv0t`lc2nLw%ji(J6=g z5O5&qopE&a=G_5L8@#F?qtGTawQ#w*_p^Qono*j4I_vb_Q*V38vv5+_bMl1cbhvWf zH8(&!iX$~>!S(W^eLK0oZEwQ?myqZ6zSCY}*~-Ah@QeawdalvuuqcpYoEoUlTGq!V zMN>Rs4kl%xtDlS$=3j;y{ZT zvCoV%gDZouL3e|e#Q*>e6L0+Trk824J+P5!eqUl61eQuZl4T@VI`G{Glq-63$tyU8qMZCL9d0@>_*2`2;f$Qd?>&TB90I3{>xLc&fPsKHE&cB2|!?v$=$FeTLO}Fw~~-WoCZ7?4($8 zjB?H|iMa=DwW5j54OiC+NP9_7$Ar+_HLB;e!NKhm9cYj)}f7&_Z$36 z0lFypMoxf(7cKO->s%WWb4KCU`7`bI)9jW91J+j&(iv9P7?af7P!xidWYJYrP8TL| zOKo{b8ofN;Kwwex;v3ZHhCD7Q=GSllZ#99+I(@y3&d}x1#jBka#Cfg zk8gR4=h$)Tr#H`|Spw^4^qG=25jCGrK=vW2a(H-Tn)`%r0w<5Y^WU4uoCO`u#;JXT zeD-gWJHn|Z7WXUC2&l|pIQ}qqv=pRA<#!H3x@EUo&MvF`Av9=L_bq6f zc7FcD8bzE3jU0K+_#T7`XTY1X@8B6W{7IoVGl;jQkG@;onXDM&8)a z?t_%EL8gNQwYFe>1v#Y4igbGrOx*H-*;P^7U;Yv;x^Xa9Qw*qfo)A|n8s091k`NOs z!8Rr+c)!-9Ys}Cey`GDq8qMAf!0eam;q#{M+n)m7F>YCYkQBH7^3xHl^#iFaav6WirMUE2-o`BoY8 z{(kFAFUAEtD4&B!`=vJG!PRTTMZi|RUG@m^xc?lmD&Onj=7kV4Y_CvBL@3&KwSwwM zfh=$9{kRud9n&Oh;DZgQ3E#j1J0Ol`xKdV1faE0q;N*x)=a9|$K^>^nVL9lY2&$AT z# zGqdFi+0o-(@nHc9N~<5CsN5_rl6{5_?Z5KzY^_|}P8{()+u|1)`2MtFc64U6&cs_q zt>v|Ak}hPgI&0oFnHuNMy{q+OI*VT^tK;h%Dwzs?gssGwOqJV^@V*Ojz7@eOZ;P`N zQpNehe!0qzzIVL{EhqkVM*5i;Yp?BcLge%)=Bbj^aO+sc<$1G_6NF zJJ29oAY;$kKhyus_YI18u&_>Fgo6R?2+xX0?am6=|8!m7jD4O~<$Lr~mSedX+|9k7 zs8SwganC>Ib9>|W=~4{{&XPm8{Wgkjzqa>8I8b}=IkS2TBT<`UrlP(nhNrc1vi~1~ z)&?&Yt-kU{o-tmE0g#Fzpg0GTa&VgV%|T1v1f-4SD?DkGQE#lkE8_#(xc@Wwu1&mnvY=33eMy2>BE zvXQEvS>MjK6DKw{xKbf9&yQT?v7HZ7_~z4QFixgp9^x>(;RUaqt}pl5bTUIFZI*){ z&ClCUQ2@Ru5>8rAbBBOJMN?1@1b>RqQXp7>e9~uhh$C{UtUA$x8`cm)mj?;83nwU# z5uOnq`Sf8-^ynGoon{fH>~=roG%~>%VHOI%@EC>wy_`0;ut~7#Ohe2p+S(5^RI;<#Wu4C6bH`f4QDFj7oS+b$~P#=2T1Sg0403b0arB;2yDrAj^{5KAfdKT7>JSYESpOraw= zfeHip9so1$q!)XvEKaRuuYiyeCUZ>rDIi)%Uy;^m6B(*0QZgva`;c?{Mg1I@9YIVR zJ+ISwb~KE)3*RO?olzt`Eo2@=vk=10mV*^S%*rcc#Mk^B30H;45-LGa1STuNdata_ z&{xsXFmXY2WiKeuAUqxiIng{NO5n0oEVU6@zTi{y zm2MBYqDD4ke$t&)A^fHJRFCQf@O^w36AS53?-Oa+o77JrloK5Oh_$->X2{uFxCn=b z8x4LI2#}#}i^M|9-s6!Gljs-eJcc%ZcjBzJ(^Zi1p%WQ52VKjHg?W5Y_hZ1Rs^Z+9 zEDHm@Hs?@+EhpcZ@>gwPQBZM;x7|&FVNIq&y*thjenZr;TP2*y(fSr5b}pFXlo;mu zT|8piA7C!*DV$ItC%jcan%@*Gxwq@G3vW@BzTrLb8x*Qt-OdSbD5&U8s%gqzzIwi> z_~A16`jM3UD%#tSD|_T($2IWbX7jE>^kKT!9H@l(N2h>OWdz#3`pbQz9^N^ZNJ)q6 z!Q-)Rrn;wFDbo|&=;5=XFX6&lA_r+d(A6~`F`6I(c=_{Xy2$mWF&DJmPrJL=ym>4x znkMsEHt~5jJziao(PID7$=KjBczdUF>-u!wFDoOn18Zh1PZ}1k&WO8*$1`{KmVUH( zK|tD-cPIyL?F+bDGe6kz`SShp@Ks|91FeX9^Ijy8UB70^{FPUoSdo0ar@fL-&d$=h z2?2?MvCt;V{R!K54#{Pe23-P^I(A^{RV;BI?K76SuvZSv+=;#FG(xBvBB>Bmdcjq& zxG20`ycgWY=-Xj5ydq(NkIJ}!A={3c=B!+y1~lv39$@*B36G~knHGf z+UiWW267KS??vH_NDDpmhh2dlt^dl9gf%^?Zp9AoN)Pfjqr*A8@e8D8SAZ4C zraSdk8-Pyj3Ljj;$k4O>@J@|Uxh>8UWw;jqxs+V(r_X;~s^M4*dTS%i3yEJBS{k|& zY_BNK;E`@asd6FMU(%l>s6!qwOqX5_i?-~z9HWrbbU4<8v(HeUrp=_Hv6aZ!ts+LB z4&y>Kv_^3-d^U%UiamruP%I2%6Co1=G{}#NRHeVNr?T;wp}YjB_BT&h2nwmw9p+Pp zf#rb3F6Z?={;t9@^D^K1%jiZ!R9f(<<-(?`42nPa2e>_gi%Lo>{W`Ra=HVPzd}Vxs#9n&sO!{@rntiUd^{lG!Cd#?Ym@Zp-fye9R`1`yvpIQ?s_z4 zEdbjTMp%)<9&sKXeJJAF-W5C2-JSd5J9c4Sbe873+pM<;UAl*mI-PrbvIo25i-MY^ z_4u?~KfZg(!+Rm3b|UXAU$PHXE=<1u+{9I671|PZ&W7t?JT(vqG$^mOOM0ZyxEz zs!cYuz?!3=ve$hwdYH*|w7AcMD=hMvZ}Pdp2Ug$TdbIP-IU_z+0Emb$p1@gF;3F*5 zkL2A=TzKCc_oXy4a=qY9olu=?jGDcb=gZlX9|5&)U!RiTojzYB5E$F3f!bFv=|ne=r{9i4n=G#_`ZZ|#aJ^gpdz=n+4u@{ zQ!aO1=tdK0*O0P8k<+gtWdbCw7p54yj@Tw+VG9RCPHqDoHXo|bGsMeSZ~Us0QqtZI zjyJg7-_xKWJ{+qXhIm`ukF|MGV5)aGtGuejVQ4gd{cQ$rdjIs`6=f`|U74^wJ;TL^ zLtMH+gP0ji?xU+|cbqe9CA&cUua+q6UNX657sxU7tWNgo`G(i$q*-1y?bP>~X-*3_ zkc77p(%Bi!Z81h&LjXV4W2%1uI6=%Ah~afTCh1abWN4uQ{Rxt@r^9wh>A6K`?sN#o zCfUs?=c~6K&FVvx#8Z`Vbts5_yr`C>#mIQkAHBllV}=aNMNP2jl4_N$ug5)+U?9-X zGi$^*c@14&r}xV~E*M$mzzcyNf2zQCFk7k_PQ~i_lS|VSzj|p<{A0&@ zEy>qTN`*09spKD?z{lTOgeqaaDp_l!t&)@Z>!!3A?1;wjIiz&K&PM3(EY|n8PXPTG zedA0Gt4uSl+{L?Q0#$Zhf8dx3&EHD>(>LMUs7REEP!Kl2?OCfEJ_$o`lbLF3d7_}m zVO$W*)`38V8g3y^f81v@$CfC35Wnh24*1ePX;&HSf3kmY-emF}gXwlHNpt!mxEq)s z)re>H&Lz)D-^k!GO4vSkchS?0y2nL&^fBwuGyssyhpsKwPUd3Hi*tQlIhttaMpq#% z{isXHcI3M-SgYEwK}Ra+MDSwo=jxdQV)!6`M!wy))htxf-7T3sgk0}TpOKWaTtT^; zWZ$*a=QzW8=+^#~R$yne?d1ew7CX{IARTylx!+*c@)5-gJX{f=bMlN@KDTL31AoF; z=YN4`B`n#5ug{JSYUwX%_z+wzc8l*$3tsp&HEZ@tYMOg99fa@l$=8$Qq=8*0N48O4Y51o&E4Seq z-NLrhlGeBAlq2y4|2X$w^A?j0wA75pea=UW$}DW8p|0pk=a2?n8I=h}L+;MLzOR)r z>gru)-4gX`^-GoWy2+Gwspl6(AAPURWZe=gN7^V(+lvk1*(9(DbECwp)6^pUojuW$ z1I5`L_k5yS6`EI(w(!i<{I+f;N#M8aBbju#jSC{UcX{|Crn~BWr4jVH=fP?0%eE-! zXHwRxedF2`;d+T^+!LBL8sRM@BVH&!L|(c3?*WH0&sm&WJK@R7u}@Lp3N{dbbM(5r zJ@}Hi+;7YnGj=cIv06;qJt$icM&Zc{GMz7r#P>Z-HKnrh;e3Oo<{;8F>{9<~FAjgd z^Mc@~c5J9pqext&^=EV`UFJHQH$qu?Q!^5{^8@?#Ib)P%7ettIt1ns~1G@4~-|w?D z-tN3f7zW>p!0?C}Q5A1{c1lF{=k|6x+5i&YyT-#XCUy2Py0F|_y~3+8CyD9bb;-#J zd})~FbA)rsbp2NshxbjeLzMX1pT4f~9IWU2W1TPIHMGbKAv=pu-)?icfSt`+%rlP& zMX#3zzo^wu482JO52P);e6KWnF>udi9|l$AEn6aTQE7%{wX&3LF6`m=gWg6P!$|Qu z?xCdsZrz-)Xc^@%mZOHMJ-?BU5IwTnXlB!~R0G$g;hu>Hm*sa%;Ae}*ue*Vo^XI+- zx(u%tV#SwllFM`r6ZskWTuK(Dx|w2F-zfgmqF^6wobwvw|0FlT$&;kkvv4#E&p>&V zhct&|f=!0Q@8LQ0iwVSW1jiXwuuCMXkkV#GB2rWq*;Gw23Qw=_w_x+5<&HcfPqc~) z?$`(`2_cvb%$<3qaGhos%nY$zd?nLpc)!`7M; z!v(3x*1}JLhz-$x-8i0{h57VC8(}>$iGb6Z%9w@abmRC%CT$wb1ujCKgw(2e7x{UR zcII<36%cqLc}Eb~l%(eEMCB1dYrn{TG#Ej6#x6Mkqa`dDhCZM|mO)WxN zG&VL?$$VWw#yj*Hx($B<0CQF|9nQGgb=WOi!1K!H9COqE%FDAKns+D_t~{`fdzF83S4@;7CA%!qax#eue4QH6H3_lGqS2xF_1 ze+9HG>mSn}ljvCttbaVXK#|VhKgo@ieGIMrG~M-z1|`j6>H6I*-L-CC#wP%WzA!vt zqtSbKm+O6?g>m;*ez4_@(TBq6(Rgu+rg(3gf0Xq9ooY_o5)48mu%7-T7%8y(PMJ(oSUB{X zRg~6m;YZM}S)w+g<~NI6k<~LbXId|bzj2jON?IKIe1G*FQ^SLqXv`(l_-(rk{B0(i z(MeKMe?qcVOzU$R5B*{Ts5WP)g}L+Vw+ldmnF2hsyd?g!_WRm`R`d4TuikDWep1h^ zWeLq?jEQx9c)wYl5D9AX+p{WS6hD?M(oK`Re-d&K-z&+RA%S-?NJ&%Y(rzP%P#}+P zatU5`oS~y>T1yb{&{FO$eBODWX}<=7KO38N$u6GClzt5D7@GYq!z$cY=~JqJ;l)pp zV5oz6z3DfG6Y&V;Eah*9qNzgS-f4nJc8s29)K-~Ov4bCk8l7x@asc2`^YSiLCTDaW zd7h2%=tR2iX7g;d(1hC<$HcfcZ*)Nlt*SoZFo z5`>pA(4}~M9AK3JyRW^S$X2;_Dk~SG5RB^W%^LYIT$xtR=@K;^IcQzmL;k~=%)F;& zwfY6#@PKdz#2o9bUC}Kacjw-U6%(1?(h1iVKpJjwJj@J27$D5_X0|C0PE}RG@8h|X zK|CoOIR;%fsF!^N)m8RdE)%8Ea{z99q3 z6t;N(WV-zVTGZTJ+3qX4I}O6$571W5qelB2b_%pitB*eggYib8sfu;2B@%H;DG#m; zJcLm8CFRU9!WFvzg6~tq{}Yw}Uq$O1Zm%ok{M@dM{^Q1K`4Kc%)qJhNnc45EkI0Ki%`H@i1DJn9Y#j*}`G8f% zs-rz$j`$Q?^YKx(adlFeD)Y{+Z68X|ZKie0o__}PMyL6uxne4Gy`JjDrwnEe&haCfkIj z!*tPT#zwk}<~r+k9lKaG+)(>x5W!tvK=h6G^U*NpyT}Qh&&7{;@eI96;#q$kjJ+U=`)taw80`&{OWf{ME=_=>V=lt%YStvgr zK0%YKtw|jIGrSGcBu$g846Mpgs4NQ#;aFgr4&wG8wO56zvc>-ZMub z_CiZ^>ngB@v~^5ceUBQ()3g}BdidJxV(PLyCs|8v)5gToL>-@L;yQP|s(c774NXzq zef%S$7(8Ss`};;}FXS@WE>;nXu~gcz<%+~s&h=tBJaQNAEL}&uBf1gocWuA*2t*16 z9E`D9M9^N5BiuR{g;q=lEGcp<%Phemg;bU$@K2}oW}=F+t?8<6vGuK!Ym&U&%65u& zSHj@pD3bD`G59J?!pIn*+x29t2lseY+@pjB&}VMX7UxV;d3EWzuZm|@t@h8Ot$-Haqge=% zq)KxuOI>pnW6WTEEb_se1rW$2yK{3K*A(%CJs$I-c zA^#h+_MZO>L@nMzc@${gp(NKxWv_1)*SVQ0w#08Mho8bDtWEHr_ElB66S|!Oa1gVN z4iw}@%!U~AvK-Z+GkwwoRz9U?SvR~uSVm^n{SUFBk2aNt8z&_ufj$ezwO(+7QQJ5D z>Elm@a4F()!%J6dW*hSGJ2UVIWAL_Lcf?PCZr5Zy=iAhbdrK@R42{o z6764i&vd2iG92?Z)Xm(!m34s>Q`L63;6cAd<8A)^^;Zy)SkM~{joMKwy$qp7EZ>y# z!SFY!bgc_|+OS17mfi;}h&WeA18Ygj5V{f2-YnASuB@KE;2JT{pcTdR?lCCO2kt$X z(w5xWrf{+Qan0Q$JBJ5|%jRaNe*Rl_*0J2r)_*Zk^BGkYr*Sr`QNzRn7)-b=i(1&B6pN8*H%<#f6@br7G!5X5W3)IXl^FSRm(*L-GuAjEHf&>_C<%5 zp8$MN%?!c5-dPV%wONJY7-M$1BNPIb=|Mj~TNJpemMJ-^{+!inG;ykkalTkGF1YUqbf)UGNX_;C+Z z97t~mZV+Xpiuy2M*)EaF%D&tK1^Y#%qUVB}rNd|T599bcHqWWXU=f&=R->iVGl6aL zeOhliyioAA1dI&(#N!vMQf>ihf9wIW`V3J3@wK9?j-GC(km&ebft^hOp02O*mWQ zJ9?R;C5&<>|AW=J8~%H9;Q!jdS2mgpP;;{QlojpUQ^tUBzp#OnEr$>~Vp4bz;*@3x zI*X|X7HkpwC!#*m%0n##k%uyLscUU^^ZD81Jy5m_c9y!bbB4sV)U}kw%o>tYsCQod z)}9ja5)Nq_@#ZEV%~~cZ{upfxF*T;G>o{(j^JbtvVokJ=u$a+$Y5~#6H2#&mhC$B2iBJ?~L$uOz%K+oAyxa^*5kw;!bBQT9||>+bN)iPYu zgmEJ(nV!5M$pm~wzuu4ZdIVFUKGfZRw&}YT&{$IrunX5y4QA@bTzw8sqvz|jZt@3I zzkB-wDi^ufeddCv-*C7{xGIKj`|kFOLT_qJFn!V-=HX0#I5Yu^9PXe6etWqLPHGN6 zlf~xWFJf#Wg;)ROvh|40l)#66Y9Rvxy%vLfOpdA>M#>&suJ|*S7i!u#hmqUyZz(CW z;HZ5u?&B133Kp;lveJGjVxS137nPp`8#y?zHWn)z-Uee+I zx>ap;id&hUx zbJeJ(HbcpR&arwop)nA~>j)ES7037bC5eBs!fk67d~D3nQ$U*M3pnY=Diz5Du0p-d zMlyXVH}Q9y={MsT5Dd);7xN!?mcUNaZp{TFIlEO_m*a{ILPlwIJ|xb2YOejXd)ZKf zP-XQaq?kj%&2#>%2DPSjvzWET#WBXMlLG%`@<1zYv}%06$+!NJn$dj@$9{P6eD2us zy+;=#5x8?09@BBBlleU><378aX|e3KEf?toATYLNgXvCFXy9b3w(gVb%Hp1gwS{aw zL(Sr!+?X@>N|t_HyDHD6%9`nfxE4qFS`GFDz)yZqDxo+C)`PTTaaaGiFCr#5O=~O#-bw0`%Gi!p_PvPnp4`RR}Ps*7aft%Bl z)Y2|st$HF2D%=sy=X}wry-?eU@0m)C2BkC>XRM;|(=6JnQ6$N+dbFQL0u<8h&XqOg&SrETcc*RqYEYVZH4w{qXU)ree(ar@)>hL5|#ly7;s>SKGsZsvukZ?*39| z!ylbAAVS-kw1-MEA$_%*_J@*Uv8o)R;+U7u*j6Riy6^P}GYrl?2n|0e@B=3UPB#La z-Df5=JM26=Kj4bC6~=Y??n2li_~2_~3EuZZ95l=-u+| zGUQ8Kox@E}(ozTX08@Wb2Olkuh4 zytoiVU}cb*%E~!UM$tsX;Ed?>ZBn@liK0yZLyaOv|0Nx>jA-~>aqU2Pr8U`QJ@Y4; z>5b-~O%cp`NErT`zZ>EdH57|RqxDAP2xc@>QNz#TKk4n1gqlbaSOunbIPLiac|c2} zl>FzH2Ca~6YmOU(;^F^W%-#xpI{tf|fmoH-t~DBJ1c5OYUjxWy=npF-U7_DYM-%{BeM|Ujb*$ z%g+mi);_R^r9`F1Mb*1Ai1aPdje{M=Ki~p^nonC!zbD=)*x`5KbH`*Elb!&STV*J@ ze0X?+Yz9V@xT`H1B>^TVA3x!$+cI425}46Q#oUZw#V^K@qG>~&F$ZSm8STL+L?(*gMPGDNk?^!Ow6{Qy`C{!5cM|fW!2Th;XUY9_fg{fRYfYetx?CP5+ z89c5xxLM2!XVl_rx;-^lR zI5w+tk%%cgHN9Wn{qT=D(J2>6A+f2yCnj7t zrabB$iuUL`VTed`lE2z5aO=5GnC!d1q6+!y$n{V2$ZHh*9myB6}EBfjiTNY=}5vV#) zh_5eU7m>N7CAqsk>#D4pYg37moy?`}xcO#cS=kRXHLEwp{ZsKTeI8#fEuTW?lJ8wv zM?63vyU0umELw&6AJ%G5*AqtjVA%8$GkKS4e=c<5rltR`5CX(Wk>uhtYc6N7ablJY|rInc=$pVq(Rb5Q3!Ar8q8^Lu9>XuyGv{ zwc>RBno}(Io<=X}`nEMS0A?knKEo<73yn6EFxW$W ze7*2tEju?u(WQdhj_s4Yt`)SK$6?N#Q3`6>5c9~K2d+cd55_=2Rx5`0$%#rXbRw3Vo#-*1*5X!e*HAQY3n+k zLb0zMRG4xxL|^>zQr7;fv0#}W71t%}Jt`w+-QhNtBR}GusH}S-dYyS8%3>Svn6yZZgR%TC6?SG-5ucm|-$3W1>m(tZ1 z-V)VLrWG&md5p2mvpyb+DDm_&V@Nd^e3dVKXeZ(`DQQHzmXKq=RM(2q%yyaXopR2Q zz$3cl%7799^=RkIZ)=%NRfcs%6b;n`sdtFmG6U8Xv}>fCOiUkUx$_+#LG#46J z((bz!sjUW=yC$-NG2>NRB&H_zCjFEg93?od*AU(DN%(4o`VMt!+w(x*0(_7Y6IQJ` z#%ge3$B)fPOln|4{F0N{BQ5=?Bw{Zjz{`{r<3kHATyP0$|MB5UOTGJ@pxFm#t0LeD z-eh^aa{Lu#p#uFHs{CqsbrfjHgxczrEYHXHSgxQ;FjnhCy6AY6*>boQ7)S2K3`XX z8eM~wr{6!wiC*Bv%CxXPi_$I<&{7G0%TJd*>knBq51Z!e$o#hbaZe6&e)Xj$^5@!SGC|>Sfdp8U*(#k+{)CwpR3!7!|e-P z6i)dcTKY?KK>+Oqr~)w5C-qMDT?k+W7RQ3#i@9=c19&Xtns=Qu#=UUg>3 znfR7eU%dpNnJAOf|*e%bGE&#!&$wVxI=jRw6kG6WA^^ZG1zZp%#Dx)2+#x z2{TGvq1BK_390?Ob&Ewdhk`1GWy?!Q(TILvRu;_RJ(3gQY$Z2s+vp@V^$b(8v-=Lj ze({gFqUHF#xYoLly{V>-wTbNyJQCDcY*_Y}tqYiGhr%-}d^B50eN8}gkiHUWr~oU>J1ye(PevQ|S?+PE);tS0hL^JaddiaejMl8Q2o_kpV4(=t z;cX*i?^8X3*@6dl83K{L6$ncZ(0Nr#{X?LYnzd?F!Yf_nF^V<{=9bD zT8I4-r|o0g;N5=$*vD4XtF_N|n$|pN9J@T_5a+A+!JT}uZywF!A8ZOa7S#bovZiJ5 z!p&mqs6!@MqTim?J6WICK@un;%XPo7$hB(9`$Sw{hP>(QyCf((N*h!}Su_%!vgkC` zn55K8`^s#o$Q^On#~mEr7`}%Zk7q%)2l}YNSf+`EJF#A0h^@gzce9-Ak1cv3?5CK>$aCe6h;@m*T}_y$zKjji zFCs-P+-D{Re4_3vb_t0sHC2H7ocR zIihOj5AtLlsq(@O~n8F0``vZ2F55*(D~6errm8Y-PDQuoOZU zT>>dKQQvzU7sSSKQ6!i0{ReCNgUuK@{Di|aVVZSrdhz6>68$gpSpU}y>}C;(^Wh}n z;qObf3jQxUnJC1?6bgFC)6vxonM3m&nTg|eV+UrQN14Ln*Nw|7^J*esi&+6QwXgcc zDfBED8WYuW*~H80YLM;+Mv_Ub-C$D5;S)YqkWol;r{Kpt)^VP!`sHR)Emqq@YtOhQeB?D_pSIk&3b)Jh4 zV)Tj3QIU+%^op~oMSN6O-!Ll^TK0K=|6IfgEuMV~t7S|H{dgfj?nfu4rX7qaz0Qng z7pK>vTV}Xin|7ILGIs`lbl5I*XP?@%-YXMT^KCf--f9&3V2i@DHVT%vA@}Xn zsA1H8={#9r(T~2@231z?PS^!*Jhp=VMj>V;ifEpb7g=$w3V9KVehu z4+@KrTr8%wFKlb4QMGbxR1vJQYXP5-bggSWj?KDfw_k1x7IU36((Gz~$vU}cV=h@A zea|pMe)C%iV6w3?9iqBT$x^%YvIx<-r8aGaDP>~JzhW`~5mV$D+Z|V_iq(ZqAG13* zQ@U%)ImsUzK;;8ck0Tjw_G)m1708zKN*DZAnmn$VxL0y^w592$|H-&>xtd|D*ZmDS zR#^2*O%%=4M}>EO(&yf{4OVzP?&x%Kb(0!wW!qPPOLnkav|tC|T=IGO3!dA?4gI?N z>rOoOgxQsTyT*s)_qFg}ENW$X8|d#^wQG>43pSS!XI9*z`8*wQo38WyEqk?X(B?nF{y*Xb6Q(|QV4ypyZfghEgc#XcmOa^cIIRMxbs`|?i*1jIIv^2 zPM`0nyw@%_IRj=l`^;NDqA}mO}e@0DxZw6wyFPzxA9*BjMM1Rtg8>)E; zy;^?La-l&!KuevT(F>_3GFyLmv3c7cF&|i@LB;JEHB_YQ$6V;2^~#Iv|6xDgpZY)K zqNt8*qRReR_>yw4%!KK5<~$iF|7^>Y8^oFtY#mRGRD4||XVsn?nLhF7`R+fDQ7@H0 z6fa$;PUxF9{yxL6I#_KFTJG-8Pd~q%tnHP|zUuuYjYT=agLf@;s(vN}iLgi6Wxz_N ze`I)1LhGjP^>_UVG<%A+6{5jICG}eju zxv}a>INC_KvFo=@pmSgbB07=KkL$aP)b1V?7f>toC==6|-2I}P78z0}n0qIGbQncd z=jEewVkUO4m2MvNKiw7Af6F zRP`H5DMZQ1T=mchUq@DEE&9GLdxKYH8=pJEKLJsOW?Iq6%Z0p!=^MQ2u37B{S@n^fbQzwSm<^+>sjpMw|lT+k~XAygHR@VN^jo9PI+X}h^Joish@^&#Q zu(n9;2NCFg1n=B#bYf~=oa!;}yvN}6G6_wNZ+(NJxu0fBJ?p@?8tWjO?e~LUG$Pkb z7F^KHsl{8fy{09ZcM9+6LIi3t&#L<+ka0CiwHkF4{c#WMsoKT12b~T1zK(1KDbZ8+ zm$*j(9^5VZj*^qU!2n0;gY> zn>Riup){|!v&HM=(tNN3Q!l}44JMz6*6Bz8cV1*O-zH+U{6#1QDD&6r``K?dU*M*` z>V;9_k53(v^lG*ruejEEeJKfW${Z80%9v;Uz3PpSdCEUHR{oVTnllYrt}^Zsz*D>^ z@R`|jpzE_V&&-qdk06cL*F_3pFk7^==C9l~#lMH4pw)n5X3o%zZY9q|3c+aKX^)0#gd=J_osF3kK! zj!1IJ?uwP|Q|iZKZ#>$8f4Kg72@({;Wm+{Cyt%iajfjNJLbMsOGvXH{fC)Wotn*Ciq)&F$)D+TOuDC@L>33MZbXjWx%v-xLi+e%BpC z5d$e={2Sl=6v)$~dd6oCL&lFW&UJ(X6kEmv$Y>dWs2ezxK4O`3sBGjO>=Vwk?kvGY z6dM8=077Ah_VUQP1&%(Q!7;QW?RH*Ln{?(sHWWQJh==2clsU%&o${^p(XSp&!HLb! z=6^f2e%)mslh&03({H}``mk8h^W`QYyy5#)RWSLlWkwoe{q_r{+C+0ECpXZp}}w5T5)sRy3L#a zQzC_$!VOg6zOX3=o!hvEA3o56xXlFpdn0iax&R`1n{`BsI~u4bARxxboN!4h7-e znORvA%|!S?huk18PV6+a=*0u)WsCbLDj=i&9122ePiN21o7&cu z_7Z>_n46m)cAT~Amz0)HSwL{H^LqsR-r#Vy0&ik}WMp3{kRH~&(}3j3ggvpe%x$}X zxu(2!R;s@|0~5|x7ypEQ>wmxU`y(0@xPW0&$j`as+AQ!q9@q`1ADyT+Cr{lawbimwqo_Evhb;nWm-hX{35QVik z$H56W_#i9lytn@H$yG9GmjV6{=$yo3@%MFRPEN?jz>5bwM$5U_=G^E;XCwo7RnRgj zH*mN4+KspHNRez4RPfhOS$dKiK!FI@&=XF?rYm95JW907JaM-bc~gl+xk;v6Wd z4a5yez`M2LIbuaE+L&4^S;5;@oYBC;u!7F!JP-D8!+YJyPk4dn!msdynB!w&x^wZz zrDzG;;s5$$VPWC?KYi+ObJZsQO5eZ!C>j_Y?)v)rxG4P~E@f}b3mkAG1^hV_!~u0@ zBg|G^y~fS&g~%ueo;u-d!KbzdBO?a5J^VZ*8fgC3NdVB-7od15c6mC>7B7Jgug&LX zRa35OmG`Su2Ub0T2v=uN5Vj7~I;r1rm|WG(MS}{#?i{3c92cJ>$_)>2xFDP%=)~|K zaN&sK92cQ{e2do5d)jz$aUq)t>*c&0iCCuP*8}bZK5Ipp2L`*ihz#4*Ip+EkuqaN#2-Vdc zp)(@R^AA9B?QbpnxLRKoyfcdm z2n0w!_$w~1!!aGvsI8X$0ARvyqac1G|!29>= zHa0dZ#i z!-IIR83QAu#(NDKzsqC$i}c(JW&yg}j)berDnd(^a_}YbUiqPeIyU#vVfF9t8~xz@ z+l1vUFb)b9qEg)dKu$%alW*`9d{Tv~BO3C|rFoU%Vh4qH zo`HZNSxSLM-zUCDR-8w~vB}k*qR2$s?#3&fPNRZsllBw<(_3X!JF_j=ak^0$KR}|q zf8Bpw0VM!FUY(G*c5=0l4u{|3^@|D1tC#+# zGq$|RPx@^^*jLOfEZ+didSAMP?OzkSj{*#~>#>LcO6xz&^uV*-WG87s%PWj=>=a<# z_xewFkgMFB7miLJo{qY~xRU@|Y<+v%Y!YOkiqOpO~0~Uk=lnU{ofq8mhX=0wwHd1*!a6~y=iM`W59FLtTweac-+!sAuY_{q^4gXtT))N# zZ(AL9fpA@iz*yG(Yudk9zmoBsO4{RIz^%y)IycVqai0GsS!oQ}YUH_f<3fwD!PyVY zUay{9FHSJd{Q?NWK5z}*GPQPdGvEL|NYBnr4ke)ic=1(uOw|DBf}fz?(%QNTn77tn zuZ8^qTl?PK{TY4+gtg7A4;=Wx_SZw;OYHB90O8(V^jP9F9v449{7ppFx4m7_cD@|_ zx7&c_BNecBgwi=rxYFST9BiSCoq>0*`)*I)vxVm*1M7d^Pg-tD3S3H@C$Rv}l71imvA7!q`tn483C;it0OcBDt$>;b;| zJE2S_NkHc+!1A?lQt8{z2szjA-~U76dLGj8y=jIo!I%iJ_V_^X-d<0$nFt39%NH1XmB>gx#D4vC}3>?FENJP+uhoVCJR%=;m;r- zJQZOH^!u~m-}PXW^J=u|#e*I$8p0Ie($aNU?|zj-94Cka<%+g~!CB?5zsB`bPtR>WgJY$bIlW2{`Z1i~rg$ z4^RnRMr%g+p|A`5fDKt|tf# z*_?u?cS3Ii4s!F%hLlNjx|u$qwS*)VxN=~6+C)oQ?*iEa@b;bNTTa3&)c`C0#7UDt zJE~m9Q~3W}qw}9@-qqaa;==l}-GTZT;qA2cbAVz2-$h&TxSFig;iqcB_W7hIhPD7L zT}JUn{rHYb@WGsh6}zwV4Dm^5pc`|$xqlfHYMbxUU}~@)(3&suOqgrzsa5di^v$`F zsks{`Zk7y~(^{&NBU*`Gc}y%z2yv#WO-9o^-2C@dz|uAwVsfmgCT{e_HE-ou=lWk} z=GaEg@WW!m(y7bd*p);14%|*DujTzn00}@fGUIjI0VyE- zyn!|>OC!qVV+ZSGeYTs>v28c3l3~QBNUz(Cf|Twtj#AZB(*8k(crLCn2ef<;XX=dI zxO~tYyy@e5ff9JuM9X1`37_9iZcSHtYzn%yIvB6q3J5+(Se{p|9ED9lmgP2^{LF*~ zaVZH_b(N<(ztpM}j$zhgGU;tYKZ2)*_bgkXO*sDu2jrYhbZ?+logMo#w$VZ31$Z*V zym@D+A^%9^ZELLeNJq&AOVX^{lBtD73cEssD@N)(72gxVlW5VrBo-%Op0x9s+jSJB z`UgEiS)(6ueIZf(MZ|Fkb)7!(^*A#3?sbX=G4Mj6SPHgOdo0q=T6H!&?b3?wEkIJx z3FbVgtI81O%o1-5W)_@L-%SggF{lJYOW^xMAOGD^pLp?De@i` z`bQ=-olZJQi$rmC^t#^C`o)#tVE5UIgrCH#Jo(h#orcXfhg-mgpE?4cq_brEmvT`Z@1r5k)zFt86pv?cP>nO}!Lh`JA=jg-7DpN1EbCpon+jXzDS)1!KW4v$Q zR2+@gXk)H_XJ$h;`uoY*cbq>pbuMwa86~HxgtwVZ%B3vGXquFY1($Bd0nb#N;L02) zNLNB@oZXE{EIUY}H$7>oE=S z18JzgBWpwh4&}Qg>GZ*;CL}1FT+`6+UisP@ea)ay74)yji`7pf%`~s3d>JA52K;gqx_7G>ac($p#?siii`jX0pC zXuAH;IWPm_U*xLEB4rpr{TwWqSk%WY_okc`GSj$uwE63T0?X5{H=M2IZyC+QWvXc~ zJH_|7f0x~~e8HtcBD>dB%ftRMoG;?4>Q#?7!Y&izT^DcqYj1x3T=;BR{A5$Ue_#Vi z7Xj9!PPh<1ZTt=0*%tnpYkMLOXiL<%z17^FaCLLS_xkxUCWUpmN-Lup*Y(N*iJ#q0 zg`=6$h8Jrh&({w==XUK}!+MLo{uCe-53!S-yn#SR-!HzcExpbcRG3;|i4pg5=@z^C zhJFKEf6l#>n(=}bE2hIWCqIzYL{PWK)%S6>Oqgh;LEXh9Jn2x?zvL;QGSEAYuUH|? zMXsCN_}+P(Q4%CyG9)3-RkwM~^<}fgtEwLG@52XskV~0H8v@#r>>Lqu!T2k(W3|LJ ziPlGlr^r&*Bxf+!Jw~Yq&W~g1#?JCx4E9=}?sjkU32KTxAKWeKpzb-=#lP&p zbj-?ZKZZtu*>9;GDgHh~s}5O?_+^8SGCA?Q;f)s=A-s9YaP-?g2<5Zv;~!CS%KJ=p z_<%=a2tk)EDTv{JS5VTevi$FBBnAs>z|h~bPYo)*;kqC}#F&u*vhnd)7G#bXf`3ox z^Z4(aT+7e$nOf$q)lLqp4SSmA!B59&hlTUQJIs1pbZ3#gW1qAJ%WN5_nUR39&SmGT zG7y+%t2%79!Q#+urS<6!VYgj&$2yShWZRw5Av*My?TaWo>7u6$r2yZ|evGbp5FL;9 z@vd^r0*-wU3EEjNMZ@XyIcjFqb9J&ykN`*DUNhI@X1sN1+{ttL)MtI@^~8)f?`TeT z&@ZUQj{8Ed{N}#+AHV-B8D{J6K44-Sb*VGkW0hUZ+!xT|2FjAp(RwW5-|b~VPC@a= zyu1+aSsBxDt?TjEyTh?J*y1q4bCf@7ca`iAx>Un9Z)SEgvPWPK{piqR9-PJNPJ!RHy_OFrm*Cl-148iRh`JSPKl=jmlXoth2n9|Y zX&Eh_sf5k=JHnGk0dL}Mk%!Y=2@eHxB06%V?LRAJ{1nxwd-Bo|P|p}gFv&O_uSkh+ zXdIRp4WmX}qx%wj*IgywGF4{hO8Z}9!wy(P7+)ea{T{p$e7Dy*p~MpIhJPTB{qZ(H zdg!2k-@p3pCnNi5K|cu1@z&Z@ZH48!^RiDXO~E*9E*bTOjTZi(hyDRQ_vVM~&*;HO7@byWJ0XLqY}o=;;^Cn6Ae8k0%^M-D%m< zQiuBR{7K(?>hs>N4@pioH4xfoam#a;=0s`!06$<3g>#1V_jjmmIgkiyo?LcPPWmDUw4wC4{pTUOKPvPFV@^< zmF0k0bmOARJ=1ufu|0&IN?N}tQW`o~+NL;lb9+~v+Ory!))8w&2EX_^1|3g2&m6Qu zPGy$FJGxUs&#cLmSauRxHPm_Rq|{d+EV+=;?t_*b1)fAE{%8DuUb|0*d$M|ppHGO3 zs#or^FFreRnBlNVQGMQf&6OlL{A8;LeP&wbTQxb9#gQ7Mt)%1!?#vg(#R@!7)DP0U&<^M4UTRy;BCl-zGc(wY<}OVHB#{o1;TmQO^(dl$6)OIJYe!fU zqiTaQ-y5qX_)LzP)Oz2c7;1j^=~+YUTB~#qerMs!pq)X^H#B;UWBSuuTQ06>9lQN2 zY35%xHY4Xv!M7;P+m)EgQgjPH`i-d=#z*#r(K1EW3r1rtHhOlP;tQhM9S1GSEZe+B zO`t>R;|8UzqeV^LP?fSR$_xQZSs!xD!ic2m0z>{sdseBv=7nrWg3B-DVfr335Yt>a zlFpR&Z->k(stXqWd5_>TahEoak4wd~=% zd+i!;zb3e{jJ92$oAQYnoR)8KDXKE6nU{`UB0+KQI@~ckdl+tK(|69~LaWy+nD`wJ3ueZ>7J$9}?VChLr zbs~O7_tPBoPHzRx0|!WYI;xz@mc zZ~E-t;|zP(ZFuT1ul&&FOyah3WzmDF&yWweJY0zDUBbvKLx58Lc2skud_U4@>C?S^Ck{OVRB~PBPGt;Ce77zp-(^O0@SKhbMps) zOD9IItNuR0D?-V7t}4N0ZrHbDOUYnwLla=Zb{q;@vFqzvA=?-8h~ZnWrYIV4u&Ibi z7U7zCdh=T2M@kjCm(B{-0ro+hSYx&~nGL~+hYi|9NF99C=vxUB_jM-x&T@~Zfz0=f z;!VK>{>V>3PK@!H<}z5+3NJZx^bJLQ4`!!mA%F33l4qb?IwL8C2$fVIsMGZH(ED8X zIO>?*pfKaHZ2atX%yYElZs3FZj`Z=*X%wr7TMgO!TE`v=RWWDAy z_smgE-Y|IbAT0P{oNm6%nddI_gzwa|78#}S8r6GY>y`;mU#qAwMct^^wMYz`AuZGL z&C`d~A6!vm%hlEG6s%}ID!6~Ku+?Wsv6yA!uDz+q$$h)}a8PiHNATXZgGAqZMSyNF z94&dXLbF0we_Hbt^sA3xP&j4v9ZC1iWamF zZAqcY&2EOszPmT7k&=Mk{k36kEH zsg{`|x;aIiHYrdbn{?k|MpFWpfO6ioe2Qi3F}5I%V5t>dIcyjy-H`D6#h6+Hwn+Pp z%_$dXOZ{$CBRXNaRv)2M&}IoFK=}nRz(10$kj}Q!D#degsVVuP`kbkIy>{+$zE?j} zc+8Q}cWY&3zw3mmhU8x=@%%*<#FjsfGFqP)rlR=cxD!N*!G{EytG{oHxg0*^JvM23 zQ@FNYE)H`YQvS+|XpV}Ep=8Vpfs=&Xz?4njJVD#qckH0kjBB!b`M#(bPD?Y7hr|{t z&o>$vXJa(j=Vq9*QfKti_!W^6JFf&%^OZwxHwLcU9D;4Y3s3!!mD!za`Tnb-usoM) zNNuI_aj+-l8Y`?^0!YTR>{pqQ`f|bFBXWE#Chn9qHy7l?ff*2YU~zmoWI}oaaaC(E z*`Fpy+Qpsr(+xi)P^RB;%!RnB3KmA(vp-cDa3>|IbA7508x7oVV`fpM(kv%wzr*l~ zbT~&#sU3(yeuTERGM-(n2wcX5IR~!qkmT)d_M&;YXl^!DO-MJKt*o@@7a2);&t`tK zLM~T0{G7oqChDag>8h*0PNEPuSIOSOyC^c5hL0RcG&qA0>v2lX6;|%l^(z1vt443< zwd3-cZddE>r&-3i-b70Rw^cSE6G?|@KkFdE%oz>cb{IcT@R1|px~J9EQBNc@ z(QPKyJ>}#%H*J$V-I8SQ?EFpzmASc@sXF5FWW=JG7<7W5-Jd1*zs2G$;aH;AtfVt& z;;F3Lt}5j(K1=$F62@miMRcfN-H>@jjcd`64;mCl=ES$FT|v1)$>?RQ;R^GS*|_CP zi*EPRu=Th{?N(5cGC9%Do|$X_w$-L_`E0sse-Cyq4qd->caIZGL!)#pyehP|yz<*t zXE5)kfhz63xPxF0)5*ssA}O?n*=TIyzWiYWkc zzOTYQ=EtD%!qb#@uCr$)syX1vaQ(lm;ySe3#t1+5@fN|-*$<>}AM*OGvB4ECpAqEU zuY<;Ov|@2~XAEVWifu%gce7?%66(&@E`#?Ggd=d!ZOmPD*yeAMV^yIBKzNeHKhvv9 zF*oEbo%h71G%Onx8uCdtJMZVuMY9z>Mu+w;#5Dx?G`31@XLkB@=H~`4z*C)(4@Yk1 z^ly<>jZKMhqf`+bJ`9QCEW*4QnT~@%OVtmY+NRFDZq)6gD1R-dLgv&&c=+F z!Nb`~WGDR+>oMMJ(>3&%2+rQ-Nyyobs9L)tma@#X`Q#zu9{eSHT5!(#apU8l8N*I1 z%c2fLUi}d({j?Us>ksJ+>!NSKPTzb2?F0ktFp}$mnJ0t)Nj($(W)Wm#6P$hWxgs9+ z+lQ?tJ6SnRH*qRV@!EDWHMMuJ93|} zH#%ZPhSUSlredM%no@I?Y%|w{{9knP`_3nH~ z4U{X+4dM~Tg-CvN{II%IQ=Lb*w=-EEmZ~*n_<{tf0$m*GJA# z&0s}Q<-rD}ft{%S-}KLiLzDMk7MIuYyTkL4LDUE77O@1N(#O2D5t3;;1LMEid@b;ynZJ}0ZR9WyjQ`^{~^s?+U z>ITNOt&b;uWF<_;AXhGWVMwFJC~T#b!VZ-2E3W8j`D*cOU+&KV=RJQ#9Pwp_`cPr; z*1cn=<6{HjJJ`1yzBdP@zq90eGL= zz)RwCVL9=g;Xrit7QLODi63mTmbnzZfkX@hZ{Ejjz;QE-`8m1S;Q$O(}2dcO=~Qq2=B7&pYnBiX67o)X|dBM7)ZV zfj&E-0R-hNECCs>M06qnZ+EKba(7ElS6pj2J}pRH+d|=3LX^W;Hq9vE)RPj?k#x74 zh8HXlJE>2~UY;qML2FW>`O2P@QouQ^(e2cPfyEGS#%G+EmZtgWXoO`(Nl052YpR?C z2!Ns0EO2hY{-Zke)5x&kC568)13WNQJm9snCnwR^VZ*CY&Mj;y> ze~IUmik7YPckFJt1Oi#tF-Pm}Z1Z(gb)l-cLH9^iXcKD8i|SAYmmQnekxz%%SQSBu z!wEkwq}c`(md>>3h{bd)bg2^#+}lEgMGGzKp2&$RwQnTE-e>&zvKP*8_9=GjaAKB= z+%7BMYDRBgA1H*p@-W=E-m-cvK-#PY7DLC>Q@EQIOuxjth2(lai89c3tGhB7ic<+G=sNS z!fv9E#O#C5wjbqcMX%L{926%S$Yc~n)$cb&N1A1IqF?ka1-d|pB*;S68$q}0_pDm+ z8}a!29ShRl30GHTg=|cZC_?x`gL`PU$8Cq-S!x%L1m5Kun+P3z@A^B1S`p5WT76|1 zz}#*aahf3~^6W+U<(SZLM8|0KJ5$ojOWnMAhYEW_Z1b2s+y0hpM^u{FeF=It)(6TB z!IqS8WYG2CyD7GDbuT$j+Kb;RN-H!LPVJ1{;2_w>Wq*<{QT)Jl5u>i2#pD}@rUY4D?}v31(_=VLtcwd+gGV`V>M=JC2r1fX)ZnB8&2E5*_KG?QREeo^2N*VNnMGDmD{njfYN|XSul|Hb05)q_AZ2By@Tfu66Ul$ zUUkRTT`j7>&UwxX^+#~k@%Q?s1R(f4M{c1Ny<2Q!JCgYTAUqdZj_13}CHF{Ij$w(! zkN2CX`Hw-vgvAz(vmlj67j!GSq@AC)GDDF{00(ye0Bvih;GP}Ay0<58FF{t;So*%Q zk?8-Ic7|*0%sX4-9No)0CXa79>a_D?wf1Q>s*)q_UV}Z?V&j$5Sr{$-NHOWP%#-g7 z^9<749Cohd{;U-tVaQ)9N$097wj~~xbg--Kw;k=r`F+ z`TGocZ(`JV!JP~*V@^am)0x6vx(&BXC~*_C-+-M{si8v|d<1KP8Qra^AFI;Kh1{wV zPOc$Lu&kXH1H_9Gh69Px`(>5SRl43NbX(nd4P?{kN#xje$G|u`}8gI^l z>@(47VEyY3(j_~yH7<9nUJO;|!|uks<32wS7ZxvSFr_$BdVkx@Zt+}v>bEu3s$XR9 z!S~sRu%>33(}a)D$h&@g6`06(njnf8>7G5b?~M6ODmD-;$slSqlC6gB2`eSs#z@|T zIJctTTCul>+Bx_--_|V7pKFlA-GL|C^pKxy^Lctbi1w~;sI_!jm=nU?y#w~v{5W=v zV?7r)Lmft%RS{@nX4pZ%vnPh7u_d5(*ur9B^x zJoTRM@c#VJNr%bg2Vw1+Dv!X3aGY!m^;wmMmCaKt=g_A(l{axUTwdEkbG2M27d<`V zE^3K4xRhE%>Dy4WVqJ_#$%TV|NO}`WuY{P;9oqUJi_$v#HbSJTBBQ5dROiE+KYdb% zNU6?o4P`q86j*9z-~Fn8Svjk-;u};Zy!p}}X+BtHh2$zr{_)}|q5B2Ji3P1L!f&V9 zS_W}M7xTRI_pjX!K!#WP;vR!Tllg@ZX7;%~qFmVM;7UM6*mhRTJNf2h`z+lG{W~|~ z6B^Fo-qyG!q15{o4^vfw1Hn^wL_Rbe4`Q1#p$5w1;Z=~KQJR8s{J93?<*%J~*y9=f~EE7tW?izb;?^Jit zPg)iaif`HHyLrc%wd-!{*Bdb&Gd$+Jm;kx=F-Kto(bK6udvn)MPQ}Q*XvI$UPKX=k zndLbuKt2LRKV}|AaI`YE>t2vMU_4nR%T)%+b>_&I{gm!Ut9AOl*S3Z&szuKhPxc1X zewke`4X>v7POs>5^m4n7i%WIu=Sb5Gz{1ab&UlJ8qJ=&}{!wN`+LW2Jha>5~*(m4j zm;JfH0XfnSqE4L>S5l1N#JiV`uY{33UT2%BaD~c0z14%k^fpkR`d0)nRC2WYSnYQi z;9l-1oHhP=OFrdE6U4(N&U_T5`%h6hRUaz3#PfyvN=_>PRBN?V1L&%5}r|EKR%fTY(zewC^Ue;qB+kWCpoP0J4jyaV~D_){ysf z&-&aW}GO%yl^ZU9qV3IKWHbdwnQCQcFm zz0MDxNH$rvBT67WjeTle9gP$a-Riyn4_o<()RN-%48sJ`g1A5(N^h4z&-EBMcun^5 zc8bRa_uZLF^?MG#XN#iP`o{m+=c<(q-HN<{817;Ca=A?>B9YByF1k7LO|qO4X50SI zof31~+QO`_fUhM>&D<^IpY?V|YI~6-+fTsOkNm_Ny;T%yUi9?afOtb6U%~-F| zqc;H9?PGVH_dCfkN|38nQMAw4+!W_|>t1MpmlwIisZ(TR(ettiFYT%!e@Wp1rW(WZ z%Sq}vc(V1P?QR=|l5#NzB7V}IlCaB#!D)p*1;5Pj`tghvYtr}#{=n!PO<2P&2cN_>Ly$|F2va&cD%U?m|&dL1$ zj(Ez=dZHHMVv%?PDGMHUmz>)wQ>2So_%R2?X?a>Rg-IR9d_hOz%E2^*Dt<6-MW=Hh51+7AYXhH&zIflZlX5<@;fqk;{yUcQq%56HI*IN7F))4#sz z|K5)E&~!hbF;IbHT_<%!BJeO~6I40n2IA>d&OUO>j@auCjGqGeks*o;(nnW|Mk5@N zO}XpvHx1LviWWLT1Ci(&07G80pLU?IO|cFMX4jMYx0*wRjXmVH5W5bKr(lW!lwBlWy0ZR52B1Wk_pHZR

cK@Ue7~0nCm70v9GWc|>o> zxcRO5-i9X3(uL7M!guaVK%4d0P-sv_79|cN4q2j%g*1P8LfOX)lWYu4c31|?aO~R8s+aDS z9spV>`$sE4daYakRNPw;<6rtyaHOtnqyzA3|q;(TTX+%cyPWiK!n4#*TZ} zi>2hSoIDref%sc@`XU?a;M^D&4XxJO3tBW@lTQt;6X1T zE97x+`>EcsKHGFG_GHfe_|5*lgyN?w`${9}Nihk37EH(Jl|d^4`dXN+@b#eI71P2e zs{+6gsdZ2J?x)ne4R@d0YVq=kxgW#(8g?_1g7f+=B>8Us8YG>AVmsG~JMytFXV02{ zpPXVTyzUfGwrhvBFyT*BXiXqYV{@?IjRwlwJA@_qg zXHE!)vD;U+NBw)*(T`^XsW4G+Uv%=IPJl5yY)iE_>~f8&<$wgS4B`&Gwt5>y=Grd zL>T#QsbC4o*0GNKGn)Xli_{ zX~caMkfX>fl_~k@m!ga{<}l3bb58VZv&9(Bo6%i)<=`>mOxQxvv7+;PLB}*bA~eT7 z|Nmm_t;3>R-$w0)C@2yRC`ijlN=Y|JgS0_Oh?K<8ogxxSiF6Jfi_W1(=^l`g8oGw= z8eoR+VeNOn`}cmwvG=k51ZJ3Lo;#oWx~}u&sZu=}IU^nsu#`iEe8$IxH~L(@Oi zI}V%r=id8V(7V~PTdpRq{#!w*YO0Q{IEIJkx8EdXeX*AGXElLI^p=o7#}o7isQwb+2-1X4G zUB%HRVW`j{x$Ct+Ok4_^^Xde({GW_tJi~QkKnQ~_wjRm-HK1<@l=kBuo`u{#`Wm%$ zye>Y3%Www~(=q^|A)uM~9?K_>*sTc+LUFu7yeBzspD(Sw%W> ztN4_IFR6T)O21T8;rIW2=x_h}w7=HBiBcy(qf_kZhYOl1397JjpOWYbs94BZN=L3& zMXfcVkAb3s(uJC~r@NUFV&rbL6m?7sM;Slzo_whS-5=SB&&hKOKVpO|mS44tpC=z| zv^vL59C3#HTRe-7+SG58KN^gV!$0lb-Kq0PDJV7#EDmX^wakobmIPoAW9!E2dru+W zr0z~&aP+>>X3@J6T_=W%?Z1YY9GAsKJ)c^p;E`yOo^%OsJSb!xan-p2PMUT%PDk81 zb_x$)sh-qTHc9?;aRs(jcVxpl*98H`n>9Vaf#qBy32dN!XRd}xBHM8OiY{t2wmtRK zBReuRFp)O&9%AHCY8t%d(@t9k|Gl~M0)QLdhzOwE%+kDN4RTg1!e-=1#)-5ZL}^p? zavtdgo+N1l%-;D=7n#1McBM5hG8qTj%`*nfueUeb+kVTV(uY#T?ro1c86(RtrFq8c z_rom&;C5U55i=ghma3(6E2< zNwA+yGebnzd4T>*4qL8V$tYqwIn1~E*rJ!$nQRDQ(q^$nHN?9xnPIyWV8!p%f}c7t zSE!yUDvVx`IY8=V@1jBhC-R<`6i@JUljH3kn7W)y#kg~`eVU}t@Jo8}v^^aPgHd(U zagCmb)jxeU!-b~6q1_n}h3%<@8IrUe&^qqs+Vd_0kZy5N z)X$s)rfH|ainYQ<&}~`vVcWzzzQA=a^O-7ip7Ak)pTyAkih^yAzK<`4tznZD@yPL3 zs~h-EAGP(^!Kxh7B_ewG;-1lN4O$+wjpm|aFw`xk&sLn9?{hR!Y4+mPKxTG*9>H>F zyX&Lw^f*WCe&u?ar^vi!PrPZ7TobpD;B)6+i3R{rd(@nIOrCDt_cBW)L7*$SJG_E3 zm1grRM|w=_^Dm7ws}XV9sJvx*+D@_MX0_RFaY_}cDcc`OKRb*aYMmrr3)@OS$Oqo0 z6$Mj(IEYVP(8qS~Z8tg>g*7?RUi>b~fA`#+n0YXp6b^_+iY|);BxMI`|4znp{wX9h z5<a9Fa}SsvKD4X>)Ww|oxfl=Mgj(X zrdsXpBXwx8l67~|O`FB-%FPG-*Rv-ZT}6=i!J-p^!eQbEAE+46@T;Yy>;PN{MYlLm z{B!%{V0j%b=Ei9|HGh~GmhGW(X@e>_V}9GYW5jNbs#MN}5w@~L2SXADQZCM|C{7yV zTt!VRYPS5F47(1jYWDq2I}J9J8EoFXW_CIwZ=svvHK(1Yh!d71uGHX46~Qej9@~Bm zPcN7Wy4>r*To8sGNLufdYoHd!8h7&t&Do6C?@5?S-*S(VG~UJ-=yx7${Lb6JH!%8H zg>7^UAV^C2B@H`!?j!u|-qc-UyPpOj=>|jERVr$223g7-eml00mp{mj4=8b^j>xcT z5m=vwC+`xVejVh)$S#R^&G+!=5TvuAjXb6p{u?kbzneWqlz_X1_1y}StI-VaDQRg- zShp$>{rl#Z3jQnWHCpmm`8^-NMOmIHT_kq-e!0gSoIZqY3PVMV?*Uq*zlB!kCyHdWX&AvXU+x&Mh_WysrNZ`=I zcMH9abQ7az9d?0_xMf?@h=sslV-QUlB2${=gT zv9L4zENO)LnBu7wcy9 zR^XgIdhnPFNk@KO=ID>V3GC~UxVAH_C~$z@5CsM|v%A@ufiAc6IV44T>T?!r;ACv- z3zeLpSgsUrLUuP72M2!{v2fR#k1+hNI|*^zSwCLHILm4S##Yzt8NR?`h|S%0Wbc=RkMR;Lo5i>$q>1VD+Wbb&}F3k z`fKtKY@(&0@MRFT@lexiR7Q~CZt$0*jd;x5alNP9tmb2h3&M{-qKJ8x z)dF!gMRpG_^w^h#re8j9QmQo#0(phjEx$))ibYU(r%Oeg0h|`kQ!?3|I1c~i?-Z>0 zO|$RY*^MMjS|IkDG350Xs%I>8hdr}=%mOZhJpk60vSPg8o=C&&2coL@w z53)!#74iyc-RGDh?D2_r?{T~-)R*H`FmEJw*OMF3kJcS!J(wPrdaRzTmdkMbn}xWr zpCoy@+p}%gU7K-}KE&sv#Ae*U(c_i6{S%pBpLcL-6CsucM-AH&kv&?2OV6^Y_?R1} zkl%^jJZR#b*cyWk*i~%%{ySyu8cy)xPpQXOZ;aDBnj#HPZ4LpGq@&KJ(8MTnpr*>A zwCVNqM0Q&PBO=##SDN^wwL+1xPp|D8lnNx~v8`A{Plzgbr6|*-2frXGGWEO;)@E#@ znBe%}qs61K+~|e7b@6R&9UDfP-IJU7pkcxxC)(ZKjT3oE#$a^mng98+)?o5RYf}%! zj{yH}xhTax0%M%?{hW@sn zS)AD6`6m?%>P`>Cscme)U~TdGox$2cRS{&;(;Tv2cTm+p{%`xNlDU~~`X9QeE`#*5E6vof zrqSnULo$`%)-HK^!`yI$6m@?zAQYS!n7a!C9nflftm^0mZh$u5(hdMEt}W z8kwGMy!z(UVZ8a8&P`#2CC;S%(WdE6;vuNW4Y3+k)Rp>N(elIKP@Rp0pYQ(nqv1 zUu0ma%zLsK=u!7h?5WYWsX)cA+SE&e{C|NJ55H10M0?zy4@9)CCpD~&OLdFKF!o?3 z>3_d%=Gl}Ph#zu3WcJAi$`(($#rs!^KN3!ciPS&%q!W)K`HgkF@qT!Cc;92WOvN1MA!_U9dV z(V~9kSRB#{{=Ht2meT2$p|-qsb*&~?PX_$ln?*9ErLcMomia5thO6e&$<}1X4G?}XRy8sW@sn$O3 zwF7~540Gwz0y}1u!DO!4`cE5gVVi4X1V!l4Bd*OOvbK#fZQi$|fub)`RD$u7e*u*@ zYMCw4{ViT=eLY#Y8Z9h{=SjOegVZ5l8N+xVyC0J*i93Ae#;+_*xYorD1<*@I4;5^T zS!yZuGDL;fh<&l88Te8CWRg?4?SV|^bivFMwl(*W!>KdQ50Mmnm*4ICYqMOFuso`; zdJd|d67VeV#MZfwKtnaW|G7nY_yAhua#FY@JwE&B->v*N5A@4pRLroyuOXwyJ7EMq z*|@lh?A>YuMql;}?+D z15gpCmb6`IZiG57A#C~J{DP{j_H=JeWB+3dt_=m)m=0nU@EF2i@YR4Kn4_XhXt>IY zjMMYmwg|W!hCDi$A?M|z81vR313VzjD{rSYMv4-)9p>XreL1WLKh)C(>f!l{$mr$Z zK+39G&+~VSS7L`uRZwu}1yEZ38c?c9@+vAgNJLWK0S(a(j}3?6oyJg^DqIg7{@AE; zQsLav36(wTY^o^I5yA4M$&NTwY&c^nZOgeckEEIGf>^p(4(o@~1F1K2O|Qw3ug8iO zJt*AjYsQjo`1ycy;aD?dYN5)R-^RlWJJud&u8P|QXBKAEh#rR~hWL*y&v?z?fd|i~ z?Lo1A_h1sJD74p$REsbVZ9054t(8zb3o*?>gvy z4h$2xJt@$gf+zX5&9WwQ)+l80^8GvIK_NS=O$HLF+QxhuU5lE8Iy92>EMf^q2~+xV z;A|Pf{!gL-2pvPTR+r@5JHLqT!*Sy1fn~Jw3?)d+{g9<7OnJYFkzng`xW_@jiB2v3 zj}cLX1N^+n}+N_jSm}1x^6GR;u0RMzBsbK`44!1BQF((YF`KZoLY$9?`!&6kWEE z;!JT;EELr^vTlBaj1lsZHUT+DtkbF}H(bySoy{NW6jBlvaimqGiBI|QT0Q0ZQ66v> zfV67!qH84@qOl?#9GTg26-3m9tIR5w8P!CiX8!~mF3l~LHT?CvsD8`h6Dal&Y@6y! zsDr-~$2!8~3~_!qK`pU%U<1=(Kc8WfxqmVzwRJQ;k>=GR5-j0}V!>Q}8Uu3(8^O} z7>xs}P}#Djy&gyb;sl^<`ug69dCZdE?wCNbx9gSY#b25kokm}@a7;tjJm46k_JF|4 zj3VzjrAtgXOy>59XIlh@Y}vZ1OmWaCIE3HI^9{{b>ioC{z)9hBy)Yd=KBU{_ObQmfU8OV zMVy~#60h&Q15lb=?P%^Va=YOcmAl5zg(lA#I?%Ee?`oILJ}YG&Jv2IXAKBU-UAQ7k zI}_-;R6wWdNEBtCRj*gvRfU^4rsA}eD+3Kk+pH~!T}@8uS{`j~7#s%+vzx0btl0GT zHJ-H*W@~zHO_25QwZ0NbeL~!MPgjb@?LzR~dfz^Ur1m!6l51iNEn1@%<&}O_@14%| z%fk#2vhyJWETj1>#JxGn{KYFMSuyw0rz7?vnb7!VP%fh&@sK$x$LNO@eg(bptQREN zc)^Z&c9*T|y%R%JWnll@{+=Dha4!=Tx$ z#xP%H9dpW9h6>o5&rOd~#CKlOU+Z!$N}jZZA#^X#7(PuGXHk8KUE6||CO7qquYSCp zmtj}nM0@Iz{83!oUOj^t+?-O5ViFnRVszjl}p&HY(1{JNoUQy3s)Ge6u#Aj5nQa4-?jp zGzRr<{=%wgujx|QoPJ8smRo=td5aLw_LV=QP(icDUeHBY;JK9c+1WB52sG75fd#>4 zzoEKZW8wRfYs^<+G5*Ax=uF=^{T?d#K9zP-k~aDp$9UbWE#owAtbI1x*en{c92VY- z1(Qp|!T7K8+vcvW>oC>P(4^4rtjsJ7&eV%qN(u~SI5~PlWH+p-;yo!G zax2rW^p6RK)}&mNDmZWA6&u#$!TSu=-j~l^S@Z?ka`<3k4=m%tmrv>=ryQL%(%giM zPZERwOJ+75+&Bi>TtT`(<_A^=G2bv6{V*g?Q32h!G7@nI^?$Cf1ZW zG;c8!K?9b2fxH~AA##xS?z(`smT{+gIs`QoSvJHRT_!}PAs&S`PvGwclfD4)MMucD z83{`Wvfuyg@8oRZLmgR4#UGdVs$mvbHCUhW%S=%^m?u}hlfCRmD=MI0yb!a{2}ix} zTAM_Ee9u^}Th&TfPb^C>u>vGT)+Py3>g$~j>eCJzb24>o{JXrT|EUZbAeJ_AVooyQ zo7Yy#IQRefYL+ju04T_qN^vN{C(;$G`?6NVf9Eou|Km7)?|b(6aFwTWxywuZJOayE zW+h3#i@-$Ae`|}rh4cvq^KviDyI2T|2jaK_J`FCWWHdX|%8gkFXejxFsdqa13lLn= z!9N9k)CCQt>;W#vq@hJV-^jvtU#s)=;h8ox8~1-pVRX z;c?O!`ylbSZgY4-JMEFh3RVli08nq8@8&*cKEcQ+yLvs&lHXmx+a9|-`+zMF$ucug zSUGNV)kYtFY)3WPNxi5t5x}Pw!ABf*zJu%~pQg0t+(8J&lXi(Zcj`qif4@Mxq+2uU1*`GvFZ4jq2Uivu8 zMdop_LyeLl{Q5396Y1cs($`OH;=ebcMJI*rX-M_(yXA;zP+Y>PzbY1I?**ETJxhW2 z-5uEa5NG%5BUNB`@1uvp$A{tv?rn4~+PUF2>}Y>j(ca_v%2!#2ud>PzjQkgWIdqi4 z%$?R29%xRw9DEiF9n#cz;eTP7-e8W3rr+w)NdEq_da3Rn9+*fh5=@FvdyZ`O(hPMo z@`EBoJWR%%)$h*cp_H6$ZatY;g#6sGuXB>I=Z_-{YBa@zz|9Q7^IfW#dj$lzoTQKZ)8lq_=R$S({FmV-j`yp4}tX3^ky&O z74fRS|Ct@Wfl5wK|I(z}v6Bhyk@jEsi$H~xj6`lI;64b1T6+QZBMZA#oq0Uu7;qm6 zW0bZpT?SMr%G%d`P#_(<5DEk(3p3k&5Dv(FIPT<(daGfttvS1%ecvXRwc!;XqGRZ1 zJzbUFSnF>aNx~dT1{B12UH$>+z{*LIgLm;@Z>L9kJPWrJdkUMfGOq0imGouj zG1+xjovL^uei?zmc-*;v+WGdY;R`;;eHoqgWkRM37GE|-)8Y;rBG0~?E<6pO`6BZVw=L|n@;x<;h5}v9i+*YXFxcLrmI29pQ`>GFRhSeVC+Zg}YT$jK;)}NLR`>Vt1UQbw;W4`;Ee``i zQRCUZ-QOesNCp6cF+B+#T_S3tx+5YDKYHRrW{6-2 znig}pwb>FvBf!~>&Vk5VQFcybN)Vll2N+pvi3F@kZtQUp);S*u6lH7D+G@ududqzD z($~4kTpuxhxtPBmc9g|Nu|YriIQJcE9got@WCkB?6(Wo}A=6RQxTWzOZ8fURdPN1U z-wc^Po8CpPvs*n4h5|X3RgX0}y}f3`G%sC{rrb;nj7T;)BZ% zU7S6Ye}0-zCCTyatE7GgW>44o^Jhp`q@!}NjD-s_MimO|>%@0xPWWIUdnr(PnNA9= z9O&9;51#-F@pF{CoGX0I+G()bo~F5&@#yNDyT3u@H&GIAMzD|16*IEy7rpioX6twI z25iW+_>YofHu^W+RmpT9C$MqIe#F&i-?rfT^VpR6oVeU&+G)7^kIJE2rQ`D7sJ=|% z!zd@7Th{)iS5dZUxEI(yzR0KXxn`xm1}_(O*07p71jEJ^{(o(%)p!k2f>h%OD;&Lu zHMh?Ql^SO(cBvqve2O(0_vb_QKk4(N+1g0x@h|v~|hWk0+^Z!+VaFWO$i_ewy zcwX+`Kcu3ce~uT!5 zuyw2a-vvAoxqL9@;y>OqVK&ms>LjhiybK-bgrHdeGlwAY1VxhNAnqb9Q~OcL4H6`g zYrv=QUfn~;Hk};6tQ#js?l{lvPTdvy0<-UclnZGX?@=D&AA2kY7%&ZcULoesq>Bh` zcCQM_r+1gOxsX`n|pJAY^X$*$!XtfQ1XSQ1T@4aixIV3fxDu;DdJRtwcfj} zVVeFnY7MD~gfRe#I>2M^j0fOwBz*44qT!0wv&jrdd^(*c!JF{1TimC4w4{@PWVfc& z*+Cmey!AQm;ScI*vP>gMKcmC%}1n&_L`^(x*3-#C}URPV$zU zy|>Txm*NpiXKI+8**yW}OdmS*+I2e`5Dt7B_nyd>(k4_}M^J!lbe%FntuoOmg%ig8 z?7e7pe@{!?Eo33o_u(e@QG#%SHr;rpy)wAxxK^<=eB>UyigZ{kOk} zR?2eBMI#;q*ZFsJ|z)HPM8i0vhJfbtwjlohHA)q{g#Y zdWD~-KR>h{#4fnTc)I73ZTM7w`PYHVjj3v{-F{`R)HpvT1@4QGy+xyKFc=Y)3p`$r zJU|i>XfMx*RNmiY<6XSk)BOCRu`bf^5N)kPAtewz7y63Vq2uYSZEwZz0f(_9Cy0P?KRp0^6jNj=iO7f2gF z{GoZ1XJ+Fn<)2K_e~w6|vc2i=2!uuuUi!zCY3!Tz3A z2<&LQhirpNx)19sr$|z%<@Hs3hj;bL0$k<#w1OVC45eQXo(PkmDDw4&qgRJ^IkWmE zW8itQ@jDf>!jU_;6^hs0Xzb$?xCv2AlvXAKJ{qh9fmCC=rE1GdV*@Rrzlf&dy={n8Ii&)Qx3o~hcfXqHJ6u!LE^VKa?vIZ$~^&~5`9LQKz7iA%K{JMzOzQf~@ z&6XSZK%kAEW6ZC5_a3_G zx_Qq}0Ga=6&3;?7;g7zxw!#ij_b?6QVywHXP`%VHd{s2-H>8_>ZLF|@JKoAV1@>5V zEHf4F?_s$%0+7K?!B)|~wr~5$e-li?LTFtypPi(|nlFUcONO%2$)*=xL z0llI1mHN+HRp}V|RDAwOxFATkWn?K@A1tqgJOE8q-S7E~Pe}SgW2|K0oY|)a{M+*A z>KY8*A#ezrmy`K(MHg+Ov5BT86!}p9?Fd$LYNXKVPVYlzR}q_h;jT_|kw-nF?DZ#i|YJ-t7l}M9zWg^-nE6&g#^UkZYPlmlZ8wv@rt6O!%GY1yGL5&YB1A%REVJ2N`BmP;Ba|Lj!X|+ znT)TIg;22=$(HcPI1Y_4HI6eKxwz`OdMNe*O zW0okZHfbWCE!3yA!9vZfVo{C7H{OIKB4BV~&uFs0+pQ?c6b3=yDS(gQ*xRm(p4_kc z6=JN-u)$Q8I%>utJQNXqf<4ESQPFO#Z~y#M~AFCF#iOhdy55 z^Mar~1Ot?q2t>YxZ_j)U`hwzVd9bO3AG1v13;olQwvR!r9DIIDo|q+HER7uBM0M7WzrQdW8VLBpTE!Nk7oh!WKxg{K|40OL(^?-upu zZ$al5vF#!-$FA@F^r!=UAjx^m%ONUy!DD->=6d@SIrI~r@Lt(dx4JQff=RIgaE!_N ze?*vfqh0A6V(!Fz?*7<9({S;uD2;^9y2Si(Jv-RN>G(-oVUW3dgd8L9b1X!)g5r-2Gx82jtDCVzU|Yd$T!n8H)s!%ep9WoTC0qK20PrSC`e z_}eu#QAxe~ksx2t@*bu=#tN4Beb1V?a6gX?Osq6=sHQeM;tp9V z9w2A+Zq8MFbqgcvdQCzx{tMDG@iUzCZdym<#x~324ezB8Ox#CijUwkZ)%@2#4y}go z3A?zmXJ}27ryv$^Umn)>G6f22c#PUFY}I}9&hX^ON`#fXjLUU;Vp=0h;C^2Q!PEj? z^M2^M$^6GMwFSMx*FyGK^6LaS2n7E+z`nxgC!W;Rm$3A>$9rJO^{0Lab$R0p#&_#N zO8-&Nx$_@9LCAk3huBCA9DcO#Yxt4*2cG{sPv%&=D%~&wc(RRswqg9v^7yr+`^sG; zMIM~iFJIVU5NuV|}>Ut-;=K%ldI^-i#`}Otgwb$LvXiZ|)ham5JAr4|Z z1P3!%El>GYz8EteDi12>Af7u3U&ARD+eBz5J>r{wQsmdUsi8kD6&~6r<+!rO37=%!UF!HU+{xoC%wq59!0B-< zIY(10Rj{%-OF)PgZC^dG;)p;wVOH1GmcGk^VqZQ&ZSL2s%Xsci=KDJWJxz+S+vQF4xX9Qb2LR8 z2;b2dcJQpR*+l4le*SF@qwpYYdJqKcP4(j-UbK*=9%}*-Umm$kGKCFP?S)^ug1g(GvoX(&ykkOzE@ePtPurzK@*XQ5NqMy? zf-)VQRWiHYn`woG4`M{o5JBydg>%Z#2F-{Iw{LP1#$mJGV7w6C@%0P0{U;Y5TIrp> z_p|xLRUVu2+q9rJHVPhCQNcLx0#!jCG6lXQpjdV*MsjFrw{qft9txrUgVZ(spGT7( ziL0Z%l!rjSD*UPZN%l8K3GgoK9g`@I^>rct#AT=LN6uA1~i{2~7zdL*43FC}w z?rgf@^#CbMSzpl}Z+biu?p_|uK?8t$A_!+hO&<;J6%Jw!34} zvC-;EZI6n6*anyAKB_b5K2lKVL}Y74xg)GS;%cmQzp+Q7{T_Bpo~n&p)gYea{G^bN z)7W~ireyCWssR3-CgCO}P%S|@wcBN)brpF)I4maWDc$8dOWINM%YS zA9_=*V^g?%Xwrm^W}umJ6*DQN`HefZVyIw;){O=c3YVYa5_}@LFi(Q;*W3Qt%ajMcWg%x8qykS<3vtrw{T@z3aPaf?x||R z1svo9kK%DtXGv9liMu3ERZ5m{H#LgoI zpi`PN69j#m=WK6yLoz~8JR37nkvn-48`k=ByF@2?6GDL=tLEb$7d(cN)G#&Xqc4x) zn5|-jU5R+zyBDuQpPLzKX8!n{E)^fJR(N(P%|M6}DU>B%mjY?HKEBtdpt96;82YI` zXw?L)`kNyF(LRPcbgNelOUQp6p%FVUrdz*0^L4Yp4@vo>K0{voPbzl%+Zo&&Ev{B* z|AU{|KcaV!Z$+AU_F;g1Ce)=`y=M(1H)@$14oeXh(T zN5*(Gqcfdaqfz3?)&yHX$sbLCB0l)?zj3+-kYk$CQr3ZuKsBEc?f=qBC>oId2j%kr zzQXce5CS5IRRGHjb@TL$urxRX&PB^kSvh#01N`#e^=&7+p73`8I}-srXp`t1_WqaI z=2?dk{hX$lml%Lu?>9UF11P^h6?9hKVufNUGR++BatKv6HcHgQW()Gl;Z;fXhod7xuVtMCT zD(prPd;k3h^!N#AP5=>pzis!j%_|eO;A^toQk4IC4-jgvdIp|(u1;2&e=tY{#2tzz zn0~$fGT7WRMgYg34}gXGY$b&Boqdl9t~R1^I33II4lwYCwgt z_uWsL7mLLnuJQ(Yk3v`CsYq|WY|FMKZ``Y5W+^GD!%&eHSyFm&W^jT10>Jpr)=y*s zV9_um|C2v}qGGk}ayRX=_@v_cqQdh1`xh>a=`A}D$GGC+Vsz~sW(zkCYh$VK`BTE2 zG|=}*&xnak`uqtO8hBS+nnROn^;9V_F>x=z>;Bd0=Dr%D@lX+nQysEZLr}u1g=5t= zW2~55nTw|&(2Y&Qq9>aE$H1z^)_9rA@b4`}fJp#QF!VCw78(1yqiFvjrTeTi0rz%#qK&oq&C6Z* zbpWOWe!(f`eVEsRJE=&rt7!e_iZBE4D>cmCH5NV)h~d4qbTIgbUyi%nOA5rH0~2o= z(q*sptRE3@TJvXG$TFl@x8x9LvNsF?=Vq9>vo^MR$iTa~L&~o?>*-KTCz~`A^l}Dm zG2iCzf>}+92=5g@NIsnhSnsQ*xK-1YOyAvD0ImNmdt#!SZzOt5cnNr2BAXea>GzhcgKnQY|J$8rO= z4-O7?8Q_MM0&)w^$mpQ{qXfXaV7Js%esx?Z^Uu2vff1qFcJZeo^9buX;~drkFv4Tm zpnk6a6-t178z4{VzfmdtF9m|kRps&7*?{R)mucw&!_{XBcrWHK2~OuY*Wz6s(8Xy2 zGIjs+c0cp_3VQ9@;))&?{g%^sLySM2Uy{py5N7rm@OJcMqPwoQ0&;`7Z}SGV~2`N;u?#!8%4cNiHXpsWZu9#sa&>dTB*3xrkSo%6sgToiy}2CYBz zINvxk2C+N4&3n-hR5T$W;mr#@Tepl4(tuWBDHDlaZgdYkDKX9P1%v~>A3$Hvc2HD+ zBLohJWWLUywVnNP*=;?Wo2=hyFsYD13u|YZssq=z;U?a8G%S&Hj6($Cjt>6lnM&ye zt_eWDRx~VqJF0c>KO(uA9q=o>x;U4Nn>~JEX93th<=%81Cm=EbZiVaB&5+&|0)3Ua zS|sb>_W+C=feZMIpWw!U*b{Mv;lmu9;62nD?n!t8 z6_q%_GlZT)!y-Wg9M$RzyScXZ=jwhkXDHww^qowYk_7_4_q-H2_WmYbK|VrF5WjlZ zEz+hV>^R5eIp?2K39#m^^IZKxR}gXbU;1wWLTsmgIXJ*avv}wwOnKOlE?z~ zgS!t!Ak)XLj=6_dPtt}mkLmycjrQC@v}f;)UZN4RmX=>r^STX~0|o%^K-Z%gxm7A^ zprNSl`@}Rz9?P2F+n%md17;GO?2>3EZPv}y!9f{O?YykCvAIc(I9kaLV@RcqFDNMZ zM-K#aY(F6pV*|YI?(Um=_|G`g5Se8L3v{=m+ktG;6+j159f0)#rXxTu!c`Ap!-+ol zz04oRkYpXUEA_ls#SCf%98weoUM({Y03wVo=X4hTfQfQrK)P_HFozlTZ0C=szWGjm zK)?DfgB_DexS1gm-Z{3uJ>8q4)ukB_(P;K0YgsxHZQ-INTKIO00m!h%Ixhnm;A7Wy^T)2e04aeSRq^?wet_ z3UTy(w}kw@W4L$YxDc6f3ZC)VDmw&bOua))%l2%uUfbpDUjL1CN~RF2of&AsPkpn5 ztSmELH{`wIXguhqwFEpar`uCcQ833Oz{t=CR6e*jo=)4XO3Y)Tua;$SPyGT061iQ@ z_szVwt9mS!yQ5xlQL+GHn%{HmoL_IIvXqD+t^+BJsp-=f=t7 z4XAXuCyZR9X1tc84q<@eq1qb3FxBL~4*%oSSZIz6!tSV%D^rq}M?*ez4Q%rF4wN-_<=h*?*BobUmDcKK(6 zKuAjW{bo5XZ`yo@0cK^Xv#6ZIrNx_h{~yK3hE|}V$IdhhY{n%5@XrjS%^kA>$`Wbt z&Dv_@y_)ck@M8xyPYMNGBJb4LAh$2c*wz*awB*tR4S+D$wa%PX6c(jOHq@-rP6DGNlZ>a>>i1`h9-c zo07Lvm1e=$j787XzwXBP^BaX~o=(eW z|6ecUjDA`8zxSm!68~yn`ad3(ewPAx?f=>k+y1Ttrpy1{4@W?t^XRubfkZVwuv!Y2 zS)TzJ4G?4?;4JBLxtRaKAgGxk&H@O9AXB2NAzgq9#}ep?Xm@(R1>#yo{?A)}M4rl6 z){WX#R;P01UvqEB=IV0+o?+GmY4jM^HMUXmL`kQ1VGHBOuvup}L9@5P<<4`?U=o^i zn59|xTN_0xU2Jdh6 zQ*r`~Kzgpu!=aO?qrMb(zrFc@Cn0{a3JTGTQbc=Ia?|5qG+;%|%Ah(tk2~IL=L|*H zxWK?io1f`vwi;Z}KqRZFDVxXry)payz^KmzJR`qwYrfRx8LI_k?j;Nh{PKRSGs&OC zvnGNQr+SX2q>Egsr+0Ouq=N=3xg=wLwBaqnyQ=U{{_r+B@6Oj5YRuuTTkRAtpuJPl z=Y+tva&#v&v!s#2UZm<3a+t**T+!Z zmTP)37X@)~afMF%ntUVIr;MmpvA01@Z+{(meSBDxgzr2o4+qO5 zj1s_4wlqMW$eLFnoH`B^^*dXhdoj#O9d>njji~URW|_?y(G29d9|}{`zrP2WI5p)= z+Rv)0?MlCf>L5yUzw@eOKR?QfMJ(dyKKi{Ld!7~4!(y}o_#W)(03K}G^X~=4GM2w5 zMXFPdKf6C1;op$$$R{)d2&j%r8w65B2Pe9bs1@y`dhR3Hry7^Bi#zq_Eg!Fgl>$y# z$&#A+WtO1^TC8y?TU35#t7&L^N=F)n;klyB>?wPmhDZ;|k6iV{bF2&%=S)l+_nAxx zC;aSD2U%5<;$B>6giI142`ICUw9sTqQ5=$6m z^?vSN`HGNe($GsDPiaQMeRt@E-Qz{C4N=ug+>zABm1-oTtCxBvDwrVVtsh*@l$2Ha zE{>P9aLxDhchCY-Ld8NjHfWKjIjY)s)^^4!vG_NS9Z?T);G%X+3{ zC#fx%2t&uJ+wRQg+~app2WWSZ;0maCJ=td8R|@SIWPi8#YlADR(u6J?8(#oL_1x?| z_p;~#dtuc!7Vr>3KwNx|=?)hm>RFB{4veek%*H>g2*blRy{>@HmMhK9bSGprH~a1; z5hY4i$A1efdyo<8cK_IG?J&V}Z=STo4_e5tdFe6}%E>Na9y5>{ixU z6BLpnaR-iT%dAeF6Z7h6*vmd9s_IfL39D-@isLg*fD|KO{@=<`c&hd^8l|rp7|!Mx zTC|c42r})0BFxV^pVViJg;k(8sD|Hs26wD4A47bB?8bMj*qng2dmT=F6aEa!3JRsk zyYE!KYF8{*RcJuJ_0(_|47=ZrT72u z^OgMnain5xzz`LpKRu{=A0BqnU7EBy@pSz1t4gfoV<}^nB8iXBcqYst^tK!NYIEwT z8XDTrOwRYS$2uj+1=PNij!(LY2?WMyhQm%`A~sivwSqA?bPmQ?l@9gD+Ji>!wOSO) zfz9hLebknL*Yk{z6hV$qF(t zw5jx!I&2xWVQ9q(8f59(p_H~BX9MFXL(m(?Y`I0 znWW&m0%1QE{Ti#G87>V;1`<+Io(pejM?0ZR%ExAbw-Mhu1!h zX({iTAhd^y`G>mDfUgwt>+&=i-NGf8_rx7(FF&Sq$0^;}dihA|!`P!z|3kg~?LaVC z?`n=0DK;&bI{ft7D(M*>zEC;C?6MWNe9W$wZx(>OnTu}_9 zK#aB%pZ2l!F@F7!`u16;Yprg^7jX^gwqer4r{7c(%N;R1bRyj)lRd4146x(^C~P8I-S)$yi?Y@WLne?&bN{vBF4q$vVcu#JQHEmqorl&Z&o=tgPR?EXq~H0ad6S zm>x$l^QQkutonb17SN-WrDF7T*@zEVy_^8MDg}EVk&T0w#zjdQ`RW<=HHxX${jCc| zmPxg)bp$pGHas6hWRsJH*Q$Hy`(EXkYgymhBHttyJ26zqtDz9e1!xD2I|fjDx+s>R zpuxCjyk|!{Yo*fhXW{0G?O$$tN+=mS&}Cg`>nKB-{=6`i3ym{#wR#Cl>sm${D8wk0 zL}FcS9~=>W7=MZ?T2+Us8+)tJtoPsEG#a2BrWkG-HzK%vN0&S=b6eQ9(VXg1Z^Te^ zV`@-T2r(xEa-UPPNF;oLn zD!=<&LhtxekTOW#74l`AEUW~cyNbl_D|8-9a3vmf%n@p`?d>Vc#D{P6Eu31--`+br zSQaI`Mk3>@NKb$6d!*a!<*#QT?(6!UN*XZJacq#M=MS=l9d8A*Ic1xVttTZjUn{iQ zTr_URHwqYcxABR2&}=HvU&d)o*vI@xHYa^S9!u$6&+kU!PKTV;dM$moko7Vs1vhAL zH-$JO0*NaYv?Rf%PrU_$cO_$>TeU+Unl0=HGLK9Yw%M{Fs}n#=6+InV zLc)o-=+BT6?)$nb-*hFOl2YL6ckA_ZiZ-qs)bIBReK31DW;PE0uR!dG1wWr9WAOGYA5C4a z#JvXTP}-HUq+U!Hm9AN?eQM!$WBBG6Gx~+lE@xsQY9eeizpDN9hSUca+$7Zqt}kOb ze5|o^{2vg`8S9lGB`o5&*vMExq1xXQ-6}E2@vYf~UypVY%_+es3cX@vHc_*j9NIK+ z38`6Ppr@!SQnZ}DjVaYgG^?3Q=Q*#UP3}I6e>P#~W$-IeJP|^SZELJ<9M9reWnS5t zqBsS1ue450;y{BjO|#ZIMELw`s?zYc?P|%n7NTc5d8vL~q5g1Zme3VaWF>hPvOynX zYKC}{n6P?H@G8fDc`OE#=8AQMJZ9=oF66_tuKpH$cLSx-9nv6L-*g_4wRYYLM1 zK~;c_kkmwJC;nthOJ=hwlTbOE6U67x!UXLTO&N`)(A-)MD5r^HRC+?p7)c1el8}W? ztX{RB1ZM9Gm}Jdi&HI^t&dOiFY(9Ky%^hGv0Rtu-L~&yR_*=#SOkbahO_dt^f5wB{ zy-na;<){~YnOZ&(M?tpRW0zX!ELix(*d{$}d1WGi_7@$UrhY5VPC5IcL*`#hxi?L( zpAq(@n4@u|S>cJtJpbg_{5N->KNC)@-b$fKbc$wtQOyksgYe3e6)lt0k$9#+*H(Z| z(#3E`ZR}|_{fKIDAPfA!kt0XC8QOKmXb0C%q{lraiDL{c^_(TMp8Uk``%Ek?IX&ol zgXLK?30n5L{sdm6l<_r{x3F}{Lfle%AcR@^iG|eZ+jUJ6_eDvKY-b^9;tZXkPTQA5 zN45Ud4<+#jEi}iG)E9^&g0)>s&B8-!Mv18h6~A>JFW6RdC~A2#9^>!SjVC; zQJsNl3+p`YsT$TrH3r|Adqw*Eu&wgf`6121nG!C>PT9XXCZQ4Q22Qyjz`M&+s zt-TwDhV0(<^YkHk@^e~^U<7CsrSM7GY)I)!X0rHxbC_&RFg5F|7-<<99GhtcmoyZg zf90(j!ra#+?|s5!aWk1@fPeTVEa+g*DAqm zu|qinvGP`iFD(N__EIs-*fHaIdX1J&cDvk z@62R+ev|I3i5Hzf>~nDjbGJ&upcO=OeuTl-tl+i%^*f=O(R_D99L6GLxtC)Aj`jdw z`Ye{UG!oFPdIHpWYgVq9sZe!n^h)5j(1AypalJ%_>jnN~e*?2{jz;$k6^QY3qGW9B z>y7xs?y9-0z?myG51gH~wJ8o-`f)=Iy~@FQvf|I|_`1ZtS6RlG~3BJbJicS`pFeygm0lNC*Bt z)qYZQV>h*sl>O9uM3}F$(l?vyNN303EHU4c#;WL|^IXC@f9g#`{8EW>8VB#<#bhK`?ZbNuf#+kgMQoUl7;Z7(vpY5~^!Xt@j@{Zq3=FI$v>x%)9ygu2*} zwHgg5`3#cr$=q~2e6_E~-r-hHS$uc6yB9139XBDcJvV_XUFS~`K89Nqf_;{C+snta zWI{G24Srz-2L}cww>qz`zAu&u3CXcg%n7@KTRW4BK7NYKhle`KKVRqM?{3fOci`% zC7@gZkS>`bM+uKm#mCY;O~?spn|D?Mr_u8W}>2n|E)%r=Yk7imHhfW@0{U zj6#Cc2zKUdxuRcu7s^DU)6?L%Um^%Bq1?l_)pxl z!a-P8Q=2(i=Y&r2+u~H{{0Tv7gb1z*GLg=035&eJy7^nGIC?+=Dl~@j{t)2c*(DI6 z+KmR(7lehqeO+9WpuVo+omAuuJlbKfv9^8Ta_UZ*F z$1oH|vdPR5kKG|t_Ggw8SQJNuW^ioCopRU4Z@%Y9%r3W7QP+8!H#*~1^{FO-4LZ6i zIIf6lj|lrH%OeC1S`gujhAlH?oH1-eQJBLeXotja&jW9}2nCv*%d%(ZYs@`DuF%h* z{vpzPlMz}Dx=A}eO4EiYGRFTgwuXJw@J+(#|tlQ&>XFL(Lk)iLW8wZq+h2 zXwK6TG)dMk$z>oMYg(Hx$rdaqaa%+Wz0BC?H5LEulkn2`)p@B>98!?*acY{t`|h21 z(G;Y}n99gC!h~t(;8 zY6|Db2sq_sNSxea-@O|ovw(QCLiwK zQ)eOD-*s?){@zJfa;rkoZ@Zl*R>pi00c?Y8Jm>P_hEn_}f!-rkl!juy*C2R=r=ozZ z_}{PkcBQ97pMmp-C_cjimMTLW7=EblXb9SQ*_4A*bl9(;L9x*d(P z%Ezn9&|%)Ax*I%MVhZ%FkN&&L3|TIxD&u_EA@@5VrKcO zA140dVW|H}an-j@(=Fj0{Xn7HD+-yq`JL0w*An}$=_ZSFD|-HT6O5)gT^iuR#x%Yr z4K>zlZ7@YwiuH+S>YSJz31qI{2oupRLU}fn899zHclpsX`fNuk_}%V= zSmKb8H@0hqt*2|&0HdB2UKJoI|6ffB{-NQnuVLkZ0AMceihNwv;X#USbaYpb zQ&lIe^?Ye#7~wvT@O3G;r5RJM9)Iow3i|BQ-NN}Y4bJVSxZjC#2_*lFWTBMj9*ET2%7nY?{r=1Rxs4SYy-stOVCQE~xD{U#QIVus@xe zZSI71bEL)5G6BzNWziSd+T|KlrJ=v)Wo*hw1wttAr9?JbyhK#qu>7tYNHwf(MkeNq zJCc}VlrfqjZJ*Z05teG@J`_7qsslp+daO8slxd)8qWByzqp6Sm(*-r~v(ZRvG1!pB zLt6Q2)2HlkiXGHf%rqQ}weQ(;cB8>VRck2{$k~22lhh``SVt~;{?I>FYv{J$c#edM z<9twvA)nMkui-5wTv_Z61P7xL^Y`J&h1Pz`XuSO*A2>YpFil#G&);Pgs0{3~AK9I) ze8gn%T#%~Yqud<5MrCwfdMnk$#TcKuO_D)vg>@mZhi95+v87k@4d!RI^%r~_F&k?5 z`S&Lkaufvr!jln~=*L7d44SjCHUB#sFG{9vzmj4`t6-Mkd_n`S?57)U$nHVs4Rjd@ zr~u0)M`j1~U5t0uZ|p+yI!V^i_jtSH&LoMz*?XvKn}>S_Zyi4+j`Y@xAg21&V-CAy zQ+3JCZ`(?C9s~Ecu6~x;a$%{C=BrunT(*j23mao5Jg) z<*K8!x!=h@uCYq7^|BU|<`htpH2X~H7MK&0DtffWa49>=uVfcNG6tslMY`ABycAtJ zR~HkN>wfv;4wgM?dEE3XwmY~QYesHdHG~vC^{SP7_gWk2wee)a727>_>Pm)|Rdl(9;28X1?rDFa);M}V zoVmpm>U8_rTH)CggeG=0+0>gW3dVBkoMQ0J2kHqvM}K|h9~X<2V%{T1Q}tOgXQF7%98fOv$d`{o zZ%&NshOv~qD)DnMkGCpY+h{1xGS*4(ky}Q1G5*^rsEV>e>iwI6)kfO}r(fXC``-*S zC4W}ka$cn5G&sLI%rOUTF0H_KFUI(TtWZ$Q{%6|kJfR~jso#g%1@ zs|{Brvob(|wq4arbKH(l=>@Oo*5kC=e+4zyALq~(!(?L&imqbP@(WyQlK0Un?KSsP zH-QAMRnJBm0&8CVLA=#SVsrw$YyZQ9-bQ&ubJsQt{8CXN$6zu>ADFOkaX)v$%R&a6E#BI!Ig`~bT)l z*Ut2OHN0a<-N5|s>who%ku9d_nw`s7qb<+5#_XrBQMbE$6h<5p zqK?rrt*u*+Obz>;2g%mms<8uoanohuPJx;HqR>v$f!$SmQK)9sIQOh+r+u&e2rxAq zM;&`)$jA_u;uG_Ga6-W6I(FkN&;IjJv;g-SOL@h55;_**5X6U?aY*mwca)n)RNex;emu2X*^Kv6`&(i3S*z6&6M^b*0g3 z>rf))`Gzh&&kjT%5q22We`7S&nlN&YOB7BAPUOMZmqQW(Ts1dU`8LCcdTQnG}l0cVZRU&OCW4N>hG|H#d4GV zvB$GR7+2uIGh=hn;q?<^vu~FaX<)8tu!tF{l-iG!6awV;N?!CoBS5r+VLwT%q@jra zAYYHTw+~}x>hATt&`)dO%SVj3CJPyG1XJpcer16wrMo<@*1q)t@@wz3H5o=x?%dkq zgQpSsEN8m2?oEIL8IOh(&GBLthrhO6B(iFk`L?xu!Pp;g>@9yaF6$_WG923J@)6%^ zzkP3MiCpCRW4bUEn3;u67*l0g#z@7DHjOHQW9H~9la=51oazBYBX#cY@BRKxA7t0d z)eJ9GqEj`d8R>akyun`fqqVE47l=r5lbrTr_mkWEbf&JhZ_@O}Ku;aCWiRD)?z_=S z4K@QbZQG*>Y!J~*-{L+8hJ?wE6s3nydj3_ctgPW&`jWD9G0AIWn8cd5YDuKoflzHZ zC`gNcYd)cR&yQi#Dcy3@8}xWE?5DEvO8LDgey`>rKp%^@j2nMfTZLb zC{)E8$Q8)(^kY3Ea`qH8)scw+b?fJ!9T-M5@BK&>BnSQC6F(1r*Lre2 zZc#=THRs1K8tIaVoq(yj!-ZU1sU@r1ijvdon`PJpD#T&cl@R)3mi5DNl_OUz*U7v% znt1CW9BR5JbIi zWb?wWCu?PpIbp7eM=e&(uE1fG{BNof#6%-HF^23b7~*IL7|5Tz;EcGUnXT!(BF)Py z4rEVK4NW`c&&2aZCwB1KMuCLqx#$4kkQS3SD|(C6xVqayFxn_P_+!=lCB^evn!P-u zF=;h1%TYH4Pwlr--Gq|2DWV{eFqmia*O@}zmxl~=bbq+LEcGUPEV&{0o2r>2=5m^k z&atIkOLaGReolQy4vX|rcr_pE)YrpKGZXqFtbaAqybnX_KQ~%&W-S%2E)1QBa#|TO zt9tsC7*0-*owR-0V^Ca@lY$_I9*LMj9V;R3zw{jc)Rg8nzE%ZISr!f@kC99^sSP9Q zBf@$%LRVcltB>5O)n!ZSjs!W-|J)r(42dA#O_p*S`bHX1yOs_&M}a^9g@Ez#oj)Dv2*U9ym3Y}2xIXy1t9tj36qAh_cpf{p$zYqDVc_NRf z(8-^Q!Sl>IbK4Ypd2eI4)9-n|_hYKqbYIT&*V%?_jq(-GYcKygeJ^z%2%>CdpROVQo)W4&`V&`MMA5UZ=osJ!KX7WTzlW4O?7NM@q2P5~h5 za}(Huy?Uj~jhrS+peSdq2QiTO*SV8G{*MZck*3SJl@1`@=*VhSaKo<#@>V(9ncO7l zp5X^0!tSG^qpuY%!j=55t%c|Kdyf2$gyKPcEe7ayxAvymEj2Q*(p-*H_!1i*jGgw# zLEUoTR8C1bkE0_8Rjb$Q;$Iz-8I6Et1vjg4)os+*Rc>ZvP`8RSW_S)7GP|K6_#~ST z7iyOcb_92i$gHWs% z(!2HrK8Xol99ozPJgjIvbvuV!+RZ1LFTS9)Uk|)|2tOr$DV3!;;N5J$ud4_cN&r-;+c> z>w1aFUMzeUc9&_z8wQ1vY4l{QNDv9@hpLuAqoY3aqa~c!GjkK+*DBK$GrRdig?CB? z!)}s9*8IMU9y5LQ_NtAUdYWkzJ%Tr&l2l37Ms2j9L`oc51*`~f|&la$;cpmv-tn{2X|f+&H0jKwIYb5Bnw z3O%?&UCU6{PUAYBzSaGa=z%|prPlE7E0gE|u)#6+taneA@;ur7Go*5*rD>JDUIW3M zeu3J+j#9?PF9X!p(UK(~;-9#dG1I9h`vrlrEunoKg4faqF&eNG!o z(2^Hs>Y<4vBIQ8V@E*N97|Unr?##Ij$*dEYw&ZCX{xEVX`rCf7g6TZ{%XJ6v)QVK7 z@=#CdiYLk5E2=7*{!f;;2vH74K9`%j0-7Fj7&u~~pFZau#Yr~?br!a?&g-y9ILg z>2UdKnEfsGDTmjc=mF|O3Eu1Z!^a%?=SXiS2nTi<+n4{Z>4}{nv94v8&Ug@%Q6lQQ zS!&@th&At#g;#2K{P^vLSK*I|+*e!#k4is|Z}b|A+c~8qGw^71KWpB76{vTp1NyTO z@sg2L-6)dASU4!)>XuwRR3(1z2|kuYV32+3r26~@>nFnZ`ZYU1o1+{RW#bM_%> ztEi%C)26fKsv0mB1QZ9v)Xf(Q73M*?&X)-aDwRg~4L@{xMfGe~`4WVNvpL4-YA7>G zfQn%qP)r3SC2{IriwA48lyutl{C$Q}1}`8BCrZZ}9hT=Ia#^LK3LQJUx_Sw<8sD9o zvbq;@!&N+$>vOoLQjYA%agErAh2T?Vvy&-eaHi$WaV}2;n7#_d5=9O3sKi8@yebN_ zhHqAO_0GFj)hk`=PI_yQ41I_&9|5#;E7}o%JZe#D+Wg~dgz)kr1m1Xk8DdtK)z1kF z+_Zk%siF*h1-Ah?hs$(2a5+fSMBng=zK6bvOhamW5i`-xHls|6nWV9D>cw095}P>_ zxWDt=G)kBrrk)9iwjQ&!W4U=Sv76o`vZ=_#2__PnIehgRl0w_y-&$gj@75KD-HvPZ zU2R;(Su*h0mLD*ir2WzcSeo$DD#S$oeuO!$L(rBvxK_uU?cDyG8^i9(0AAJDzIJ1u zDH6;`@N^5veXfvKzrV(S%Qtca^*C+`2LL0s4EXsDAE}cqEz}>i*o=#$Kznza$yaak zI?_uSPjeZ5#ho9i_KYkNs=5wVGU z)$v_AD#|e9k44g)k$*OxJ0Qc=wPF;K10+QVZ2m&!>kq#e+qrnW0>8*`EbS+Ln`)hA z_lUPHNv|H$hQN%N$XYSCsOxhj{;iPLlft6P2dUaI4Buj5a-snX=9h0mQzxTA85sF# ztQ(aN=GB*;3&!t%$ZC>%zR@GV=t423Nr`N)GH23P+3%F&34&MDNo&oTNb@C|A1t6> zc}5N_gD|wY%4>ePo}Xcb5|lqjZ_)>VQTgM7)3+`v)YzA7WJgK0(LTVlj=h*wr`F#3 zI1!+!slaqt@>&pJ9EQ#kI~^It6Xr`BFgW=46*zy7A@t^pueW8{Z;jvJ(T^V(O(%!` zo;ph9fT(HLH~BB=&yqhrQOf}KK5upBdi4eXQ;fgjctxCS&7$Ga?hqAoiH?Oo;j#I+H(A>IabQUuIbG#@5J~F2lpdXNgsq zZQlg$XVQ(8Q5oNS{8^~{!tp6C6zwEF!MYITr$s^z2}8$oCzpXCsY$J(*^JS5Y-OQ$1|CWx{meqSARkoi8dZD)jj5 zl)+j|w@{i(>iQzKHbvClk~EL8?hhKt1qP39M|uwOSy2=HsdXxUEPu*0Py`aPKSNTDZ`O4XKUUsz=H-Kfi@Usn9ke!YP`Q#>VG`8@VWdN_U?XS@+ zBmZ8Lx#xSwe?wG<2cX3=$l-6iww&0-b3LYM32dFatD>-l9*UQ@SNZj(D>Q~2myHab zoSWVEctj{j`Vdcz&J|^pllb}^Dq9M5<6ZiiaF|Po#luLH%$(qusMf=>e07B<9M+IctMICt8o@45X)C8?PUk^7$F$4~OjI-R-su4n{eMslj&O5JzA;=YmY5hXm?=d%`8 zPe_a7J6Tb9NO^HA5IMw3I#H4`k{3Ex@BHjwtD~Nb=vWsr+(qe?VYV!kXZ|eU-<~Q= zT}{N(wfD8rc52(HTbLh7T?ic=mvyCX{vE!Y`pzugE=pP%>St%st1>TY1Mv1zg(bQ> z|El5IIZn<0UCOkf{84|A^KH*X5Gcl_M!MN|vZm%-3*CKhdi3HX8ZGphes#xwC7wPD z|7)6YLRSq4^PE@zQA63@yICnl10UqAvUCBdQKVaD)$NoO{?KpGvkT-pS$LMwcgF_x z=&VuAO3wp-qmV_&ic4qe`c#WI%cs6wC{T#BTh_BI3%@Iqx~EuJ8>S-GRC8Al;p|QN z^X6PGR76bMj;hLuBHh@CX$vXQ?Ga#)kg>erv1Uho&;D&QvVE@IK6aCwABVKV9*r?_ z>@v}Qjz$HIehd4%Q>0QOX0ktDhsGD@wL73TM^p|Mn@DWVofxXLfS5Ndkm0vbcikR< zi-4uI4}cd1W^|&KvS7q_ByUF!AFm>+)j)6Rd)5?mHDD|>p|`}pQ|CgcrA`>sETU~q z9|j923@4U?n;oXZBhWt1M(Xse?}`W^j>eaD8$S#v+nbN>sCP%I=-Yt}Hz)h#@0aow zG6V3pvbL5YcOmCJ1}@YIF?EGhV|lruz>fVpH270@i%QV_b9+^^FSbAKnemDGTn5zg zAw%biwWKyJZn(54N39!mxFt7iBq$0p_gT(4thc8`aWub#rP7&4X?1zNC^YP1%p$r- zv?B62WdX6hTb=tipA`q&u+GPdtuv z5^d3}S6J1U=@OztsLq;Nc56|O$v*SXjY^}MtKhJ(TawZ_dxnjdqH~`!{_jVhlZ!X=S?khF#SQ)E0%^0xdjTr+Gj$Cdry3QzTJ~f`E0#M z?KM%>YQXY{V8@G|o!3U^X0+=U7@QRz@=tRXp5t`J-D|C~yt8wm55u1!h8%I(L&ZGYu*?Z4<-h zmeHGvd4FE84f@lvbtmtK&+-~Te^q?ym*EB3dA*#e=)Lc{5&*oISc&odvk|VYqN!V$ z6)Sb@M?Ds}FYE+p^WonQ<;OXb{9^Ez828xSUD5bq>?mT^uXkGW-4gWI^A+X5v3DE} zXj!dg`IEDG;Awztkf~=#c~kG6SMdzfMnLI8$b$16>CV9~dCM5X0zLA$cAi9M(eUnf z>qhm^@yn#>V}Ym)Q5&DO9d)WWrm|xY5XNZUyVv+!1W=afNxh~=7JB=U?CP^VwryIu zzR#G|YcrT6+o)EjeVCP4AFMB%fEilCXYX}rGWdP)kMnR@?8=lp;&N-k9UJE&1)8^2 zBd7@D#2t08q^CXH*Za4}-6)GZ_Re&fyeAdrvfk-MdT0cVIFL7jWik(M+t_}xs7O7( zpk@S#Zd^Q}9T`w`A=D)(r_W~`D5Y22rA(jEmh9Q>_3U^Z+ALwcE<|@iqGcxPEO#i1 zqFp>NA#!2(ESS!dfyT#yuMJCs0D;M_Fxo54bkFsL-{Z`%<2l68jb$8?LC&9<>^w{D zP`bEbg1fL#I$M-0EEO3yB><~M=j8&tHoT(HeVJe4dX|iV*VnR6X|OkijLilxL;@L@ zTx3VdEI3||U6I!-Oj5E1#GWtfyO@KRurYq9v;$Z8Fm;;78H>FzpC3jk^ZGvmQ`S$XE&z?$c!IFLrM*te zXo@Bqh(KM|B;PshfV}J_CE0&n5*OQJSLCq7eC9iu?Q2nh@l??JVT=WWqNoe-XDxjx zle*vNEC2Xm3QK=jDJl)5CmDO!+Vri7f{L$&)JE4KXx^=YYueZwa$upp#am@!_bcr4 zm#=GFVSA~^gBG)}=1P`#&_5@S+h?1SI+K)P#O|ki-Svv83z-RtQFcamB{sMZFTTG~% z0OMO(ctxjHuDt$+*_#bbMMfq>*^@k(rFr{Db#W9cnhE4UEORO;-{7j9=p^bN?2DnnGrRorQ zAik@y_^JVI;NkYcJ04BY7yyml0Q(+Un^GXZ_owpo3d7ylgrbebU#0gNTZ-JNcp#ms zAGe1a%i-hBP|^5JYr%RrQyZoGSo*o?u)jyR4dx;?SNSk;NM1c5QZ$O~LTIt(%Ei@; zb5n4CVH}o<%|+2EKC%UGi-UrpB$vE){*xn9E z#kiksY;|X&w1Ltq9Iv_qw4}os+@rb zI%Lrt?zr6}N}82~6^vN||MXmXDKmx8qC?VmG~&K? zPsi%+muu`lp+??~qwZfcEdBKtqCrmb{l_Ttky|D@ld0g`cgWG{5rOyUHbz-6i4Z_A zq|=QTx4uTGY9vb}1WKfkL?X`LZLd;c7_oW89JrrYcmw26BtbrbEVew4`Gwxpp%>B1 z?@)iMz2-_0O>c;znH&aPbruNpi`e$^G=hBFq%OX^NQLCjfnc05;-9B{lz~|yqVL6x z&YS*KtKsjh@B5b#A|*pVXH;#;-Qvp?749@PT%LcUeXd^_EdigF!l9H3eH=!oBOM5` zA_}em$tV~Q}rCetW+ra3ox2;ogB!?BxL}(8wzW*#W zss1g@)oeV5SQVwDoc_C$(Ykv~SXJI^I%Yh#jZ~dVhgFn}h&C%i5k~u6YQ%kBN^zq@ z8txaOSi>PeS_w;xj5auJH4`4+Rbd*jes^PCfDQ`RNh9ep(o&wCkBJjp@Id>}gXj^| zPjLA4*gPrLkh#wuqKVdLsXW^NZj+3V2oYyCJ*m(_b#=yrjot>>FSr1oipI>{#JWZw ztw1OM9k82$<%ELt(7oNp%k_wy%~&CVdT%sWBpXO2(OMNI+oWf3B(mqb`bG5o7Xv1d z!+cQcIl99Bek3!J$L||YWkXO*QWymTgxwJbo2i_%C=d~kW6>ZSWqHu#2*-_deYWd;HJyc)rA##Fh-7Q7(E{5m?C}nsy5ebS>8|)#NLc^)7AKs9 zcX15Yvj<3XyQ1Q_2Yy=jiAO}di8bV2u)30im$AK=ZI(df>TQ&pUey%{PN?KZv!kA8 zIaVUgMw@WnVmfkfnOVaXWv(yf64@T~_?-2_lrRLnKnQ;klK8wh+af-rRf64LZ%H-6 zY)1+eGFTr*n0!A&TX69wpDKM+ZRgjQE^9)hHuGgF3&=E4vTu9Jc{z+m9j49CGrwEP z9&#tMS&*hi${I*C+w$|pjBP#N(L?;j56|MqKDXI;85u>BB<)*hZ=YJz5(~SN55tMm z2(w=oKsQ~fi()0Ccc<4|R#|4iz8?}WovUI};RGjUv+ULfx{&m@ys0s1zDji5TmjdJ zohLgI_BME_l)5{-KK`x7<=yp8?bV!WC zs+f|o8`P!+z*4Aob;^Qyf0i1Pan;@V9Ec^EbGImnYHG{-tp$^dk5Gu*-iOlo&1zZJ zgd^w_v;A>@N!qH4dq4y=n|!&78oy-JYk{uu1JbldM8>>HU^xg zAOWZS-BxIouXf(onbmBm8Kchmnr+eA=&Z393Ne%`sHaQay^o@A;-rv_SGtQq3XP1O z_pCG`+KFfb%PWIs8QFiEBh7DtF9J^XI*q6+ps|?7b08)T>z1!C`C-QR6l^>n`aj4P zsgNhrJxG>?pN;oCh07?fw+t&`A={J+6xp0PqppRro;^-^W^)UPhUBr$4WW0kIqsu{ z7Xo%otHVz}{~n&1&!9aOEDAbBMAbBJa1K0i&KxL^`n;WT7xv@uW1)&XSR~427=4Ds zz0_Np3)fMc$wO?c?WTaeu$r5PuWE(yW<$vAEr(I#p~d0udV7ujruleeakPXy zc!g~6y3e}7`Aek<&T0Im3+P2k-fZxK6w)NMcD{h5*q9I-?Z~_;l(B-ubK80yLmE-T zubmr(fKgY1lzYKOzW!>{u#~Y(<0`-W7_!ahUu)Uqv@ zH1}HNA&X`a98B#Lu8r} z#SQd+TZnq|PFcr;yqqW7n=O2JaDo`QL{BeA;=79;j(#$}Usc(>2Ai__B=cPVi+Tg_gWX+?M%9y7zR7 zuhKsBlUga{jV`<{J3LlBH3PR1BIU9QJ^R$P;loIh%{C=f&i8?}^Go{0Bd!s}k7`B0 z&y1~XR+uN>b8oz0*&LAPem_4i2R2|?K(l@D+`fvMM?SfqtH;UvJ`);^kN-i0Cr|#F zPH|^hB2&&Nas=^lr@INR`w6TRFFs=TChCqO_kRAT343T*n7nU`wBSqd45aGIGPd(^ znU zJmpvTxlw`1yj~)@6k8(*0YzgC({3scZ!g9Cg7CBguY{ChJbg>mwNxB0yo#r+PisCh zR#ikQ=8!YlrCgBx5n2|Om7VeZra^%>PR=de7I&$AvKuaIP&syP=3E-Bi|UJ+wz-7U z2|`2r{D8oCHsMZxvYHuESY{@%m*pP2-qtB7no8f6pQ@yP^GIt(2ckdVir}4*N9?le z=P}8QKg<=cixh^*DgbpN0K|OyL8d4DLhR-=n0uAatNNh;DYUNwk%L%om5_u*pkGq+ z=>w4s$`@m2Cvz?naRoQy5hl>=;@pHX%h$vAeNv);{<;$;iDcM2We8eD;;ZkI8&ggF}9DAb@5gMI% zv}k-dFv7pmvav5r14?a^tnmv{dsMfT;W_-uYI>Nf?E|dd5skqpBRl`T{l-FyRQL!` z=9Xd*B4qyZthC$h)Nc0iSt4%R!*laWz?{dk9eWN#(^8j~uQ%w;90d#Sw@>pPx2nbJ zaJTdz))K5MZGqxfPmdPQ^uU^L-3I55M;0m=mkdAllgC55S}s!U{oBG{$3yDvFV7=H zo+u51Wpp-f6g(kWlM?~=;U8X9RQ+H*K$DYKnexH)AER4v_v-S!b8IkY=3YHSGohc= z9e2Ss6M(_RTyM5e$84w{M%VzfGZTN!7EfQkzlKQHVl;f#)qV(JNm*9&x7+OUGyA`~ z_Wqe4%rH;slqwa3MjY1UJXbXP{))CA+xPXl`8b3)#0q%A5;mMWQnwz2%m-0&#$<@| z{C=9!-pZO9N5{Pg;d6j~H-c|wCt#&<417r%QQy)@R1gZFkS4n}yJpC%ma@Lkv z0yG$Cto^leYcI*GSUE3B{I8#MU{5IC#sEaDOKWDsEe_9g*}r%xa$vnEMBm;NjYI1w zDc?y+>d-pC7*bAulDc~CJf{?r!RBiD>CIN)6&@x}o1jfTHgY9>Gpn7^(KawJASl5{ zl`SkR3>AIc$PV=9GjO5VsBFoTi4h;!bRwDx8?iX@qK5YV{Y2iBZ{M^0X4-};(9BQY z5JN_CafE)p;L$2I=rpC7l4P{oLVp2ZnEa@P%{`g?Yi0P%PY@2=Pl;1E zdcRejgHzKPXe(o)PKh#Jx^LQL)sRFV{>#Ji379haHFt?}i3()oV{okpb)kEsoR^!J zcvO<&Bf11PMpao#5LaN$S1iA+o|iixeIvxTm=o9;mVB*pq$~fVrGAXK`wL(pecd`G zu|>r~rdl%4_MC_)#w@^&@abdRQ~Eo`(B|)|^=x!><$-v0Ebk^#i+CcnXc`|UG&eJ3 zrA-9raA7~Fj4y$<)ZvGxXyp1+G?kwxg+;9r2E3bS{(W2I+x}Blb>GYl7#2 z5WEfGker4TIhwtx7QaPvI8#vCcJsA31_-AH21pho6H|`G14e}@nhL2>vm)N}4A<0sRNxbR`z2TZ4j`EpBYH_@EYN`=eTCB2U!bN;UH_%WX*keC%Liu{+a6^ zH=qD#-kD)pM_a(@AD5g0a#wwgq3hC}J7g@@5~o4fYzrUx9pI z@nKFYeLoiQ)Ui0Ed`7v)zIsWDzux4an2OYPeAKY}V-2keC3i~uMpXYvVMb4EO?Y;; zdl%9w{>Y81-X37Okf;k;E+A$l69HZWCarO!%FVM`PQeh71WGd zwRlqLGdDdf>GY!67@vM*ADqBnjqYd3tvP$N1}z4GM_>mgMP*Y>6sr36*$*Z@lcx>o z0s)y3^fF2kB76ZZ!$qI>9?gwIYbe|{<1rWKvbJH;f*SGe2^~gpex3)Wn9~1E)zVf_* zq+QYy;(h2^GFpZ+ggwxBx#v&N+rgNZSz;@8N9=KW zHia>bWWWY)dv8FpDaexM&|5SrAvPe~y&;?o+upNXE*1n;i# zohM*rJ47P{(S-;Lt|DaWP`$)bM)w$CHYVjm;KrZQT7|o2l?Bj_R#EkaIbDpn=VRL< z^J`u1*4fMqYO0)ar7UXo+#s$~A5`8Akj#23B+;H$oKC*qJT&Ms4`Sk2D5qc(Y+`SUiS-g$9tx2w;!VydB znT&}^ofX(P#Igs0LuH;Rw_e1zHKP6@F(fk)_ET#05&wg=yN-(T3-<+Xg0zHmD2E^Y5mKe@kgD>w{HWQpQeU0)qV>4*g3inSWqda-U z)a(^#xl@H@697IY;$DVJeFPSS)7BXNzX+!Ur0xG}NYy6sdRi~1>d7cKD8=h>k_+wel#_dUz>2GTGs&IpmMMqM}p(7dGuu$pt zG<)O{?{fHCCgllK@`OLRpb^5r_{-Y%l~VlSJraz%m0UoZgdqThx`9?8CkwEOF&Qw z6cI{@;#ZzvGH7MOfQ4bJA5bIa&^UHo_>6lRtN4fHY1seu91CweM+Ke#z$YyvifD}f zn11dV)Z+DIJ zYwrqZK8g4JsuuQGE4g`2YPU|Itm&{H*<}1R_fII>+CNX;Bc?bwI3JyzwY|K(^}Tf| zEDWWOM-{$}Ac4O@VWG2Ihaf&j*S5|l@w=I*{&Q&4Pe2a^f1GcCAbn(_L3o|oM*94C z{rr^w$u*aMpU2tnqO+L*&?#>{ky49X0PuSwrAL@vF*nHy2t3*IK}!7qh*+2U^sD~z ztFHj^`*6Ya2Ayte`@HHR;Rztw%%&IP$@y=dmM)oaj_3ov{La!1hn?KKZSnePVt!$v z%EEq#STB$@q1ct6i2>kuih8I<4){|1FzF#IMPy5zf{y|y;Nn{@k)bF)it`?*@ezOJ{Yx@Cmm9IrE ze$)>*pX|FKh&`_kpxwWDfbV!009N15#hcOtPoIi@*i(N~zvDcnz8j{uuNCM}?<4U) zQ#c3gbkWm`#zl;y=h<@T+KrdH){e`R0C@T*<^C8W+(zv6z=>T};NwumJO31504%q{|^Esp}$0d3v z9%zv;QdG?JT&Fo-7i;Ch0suSnjW#cRv5|KeK;pB6G}!|z;+N;miI@l&7~b8agy zFAoeDE|-J6wR2=xRQdH&o>PWB50$y;>3ZhNY-xXBwn*n!R#pZ~@hqRizO()1PT-e; zqd;rmg1ZW2x_V3*cLoF!i249-___MFxTeoaS9pEvJg@;-=`ee+wDjTTKbC!J=Jq>E zTWrcd=>bdE?w0$V{Bqr!uCmhNVLoW_y<7o6^BZLM;Bw(q)?gU0%IRin7~oqc$T^&T ze%b#Gkaq(dECv9U9V0&N%sc{sbHHPl0FEbHrB74Cx^8A6GaA4GkCp>u`nJWg*6WM2 zuiRzgPP3&=`#`lu^u(r{4{$y6ZDO*pS4aeKNqUuC4_e9Q`SJx&Vfbl7i5b4>{bGZg z`eWu68yXueki!|w%)gx$Wx>W&CVQKkalk!EKk$AP75{;<=OOTRmwLSf)|-i7WvM;z zpMi7}-oU`X@Y`a5l9W`!eS1nm&UHuxPVGPY$0pu>s=};n0U*Q`by$Hj0c`!G_c|58 z&;UJSHyN>vl%#P`CVwN~!s6qiz<0&Y`y36CDaFyt`gj~<=x4&`oI8ok4JVBNcH2?H zV?R5{?E9JDZY?nMffBAkK?)0rZ2($N9V%!7sC!Kx%s=El07L(FoRNwW(16+uc8sU;X+kiL{y#NE>+#ms+gwUN1O| zZ2I}Sxc71q$RSw5m9ysY2PO--Q_-jVJZ_Xv*L-4!EJw~~fGLY}&jTv8T9t(-#+yL1?49Gf) z33~=LpGD7=+ap2E{GNSkANLlTZ*m?Gt#6*5q@xu)ub=t*kf&_A0v|jFaMeT^!1Z(UVZUuXi?SQ zzm;CfU0wDdTuZvp!a|V76W+MMW_s2^_0h}go$OgVN&oBux~6LrJX^gm>)5Dqqt@4- zOuk=h-t#SAJ@TAx{8a7(nBj?X*dsZA&C48Ve{uKi?>@l9op{=c#T)`(ojTx)U)vil zQrsjKeES5HN4WqaxHn2{ffI1D{kgr-+i}3skO?i-GqL_3R?n|i_JMJtptyRJg>9O1 zo6z{j(Kk6th4&7apattMP`{8SSSBpOzZXa>;C1ror2BZfI}hCDT-|h;r&BE5(B-Wc zzgoZDsOJByq%x;-EKC3<&KloWGRem^!U9~da{NH-#SO>qxf-XkIygx94vDWSAjhBbo*&%^=Qk-KhXAH;RMv7~ zE8%rqbcJ@pqCMx#*Mk39aG5TrpsN#E*MDv-f5-YYN?>kC5^LVnIE;(&QM_6A>ks?6 z*KTE$3qGPETZKN;`=-MW1S(2s3{!FxomeIu0$fqU-LH=2NOuBX2?F=4 zf0fJI`)z+G{9{dCS9}1!u z{^_#lP@b_xhm056s#{)@0#ZUrNmELe(1j5+MN%#jAPF6UOZj@EfQG{IyQo*yw@>=W zr)q)L4+C7RgYVwEA~^a()-du&TkOuZ+L~b5#1WaMVQNkTkdcMnoQnkZw<21iHu%h? zfY>&nsmvis^tA1x+D4iWQfH*-%{To*lW}T4a-v!0%FnY70<~K%m&m!tv5Ld!_D+?| zICJP=>)rP2gx_Eu8wN(Pq@!)@g}#qgBx1E~_g8jVh;Z5K##ua&k^vNvwbLmJZ-&sp z^!V;WBx4||(01rNu-<)dStT^Lk1)a+(Xv_EdO>p;qlByiA|)%blr^?NnGwGIF_jJl z)`Mz=Ly#`nvOLKsq$#_cD`Nupqx!>!dU7eo7?{6wt9PpQ29_xf9A^tNBY#=BK> ze+vE_ti+iZe-wzwbny-?cAUm%UPCiZ0KyAzaf z%2qkEJR6mjhtSbyZIbvvKh1`0+t^gRSij;pKR`{0&d-NkpWvG2zNds6P26}p%g zTH;8AGU9vOWm`7?IHA#!kt-P`CZvhu)G^0XHlgM*>b%+BPUbh-W=tH+DE#_3dl_+m zRD+tQDb_JpdOOU9$|+lrFVn~n7oL(A0n|3qBb0x;f-*MCK#S}IE zs##!iW_`UCE11xhv$56gi%#%?c%5)>eWnDp;vY;CVT^3&z#p5~KMt;o=T5{VC2j&M z0V4Uj<5T>MgG!OV$XhuIt|`U^5CqxD6~qg}VY{N98D{FU&o$O0@wS$B3h3tYcit6e z9gLI|PU$2>N2lOcDlrLv6=wgc8sJ#>-p&5&@sdrb#~9(Jw3gTCgAL}y0fguL3o0DM zi@ebg+^8@{;opWn3iwoH4~z$;lJ>L5vT=!=mVtlhnO0A&c{zwnl-ARyemiF5)oH7d ztla5Zkcybt$mWYc=oiy2T%v~QL0|*^DKpuRN?sQmuhHHQi>eltF@-Kui|JF_bQ%ro z>jZ9czdJ~1kzOO`9~>EKxRZ8*(P3Dp#p{_+SK^HPq;c~jOXXs6`A&P9>m!c(Q_p^Yk!fy|l%LSZ zsV_@lhx4hPHLfE&co|uZs}?`H)so=U--UkG$JT=k#p*eE>m@$!MP<^h*3BXyv0Y>) zB(^1(6S()8kvwF(QvYlk@%H6UIN^S>;z;MUrOzb~vuxiR^9xA(%Vj~M3t|?9MYP4l z`q>Ado8m0(+Z&X9mV11Qp6TsWT@jn%>vy1f@oW0URw~q?iL{E6;<%I!QrdI>F|7Wi z2vS{a%7ks#%C6x#q8sj~=$D}@1WQfEs&l2aBaCSnIz}eoC7!eNSw0u)*Qq;a7vQ-9 zuTtV_Z-H0(E-`6{f!<83Y`&eQ2XF!T*VV-@IrB2fVDHObYyzQI2ZdQ7lJilZkZQ+u zA4k27l|S-Rm2Bwk+UWIiA|no;yurnVLw?$bE86xg)vKDR(VwxeKI^xCdq}YOaIE&M zCb1&w>b^@PLVutl`A8&LK>j%{iN!}~&Dq|g&edQd!r1n?2m7{cI6gbEX zqj#(7QWe7e?WK^3^&N}UUA5nCGOn9cF|RABP$C#kC0W_9QyFIFlSzu}08!UU*EZ|7 z7i|42rY=B#s;Q+p0?vK$Hpt&0+w^DYy=E$G2e3gRejL%jG$v>$5WBzioniT)a+4~` zdcm?gfP0#Rov`0m{+4!(fO=Asw!a+|PX3Tm1X-^a{)j#X>#v2bCX2}BMR zZp-eSvmK{|g-P3)c}Gtc@fLtlOGe}(fuK+@YQ`n3I!x7!0>hC}*qAfymhLc65x!-L zXB(wD_d%Iel{`_E!$xMn!u8T4Rq^+uu$>Q!)1xuI94eB7=~iCClWr?-a$gXPL~KfG zR!-aJ>dB~8T`N|WHNVccNj)5nFHaSA9NNGy6hHn9 zkrk44YG&Nl{cDrzIRI_&CbvyeQtVd{w|w-wZg8l)>!6QWYh;Sb55Ia=|4RdMO&n4a zrdl10F`H*Uww6A}+|@2`_TYeRIbA&}Dr8dT{~Ff2gguw#L%b~y@+$e#5?u)$orr@t zrxnC3p8!E=o3mtb&%NcyF|jbRzR1iuOZ&DTgWm@;8kYvdc6Y+ z8NYV;1Dg@gb?(Uk{hlF2QeN=Pw*HeC<+(0|)!6p8aG}l7MS5Be&$-AxXsR&56!WiV zn0rS_^-tS9xwJl_C9NCluHAtA`QUsTEt~j>RRm|8X>}DaE-f1LG!ixVqvCT@il#tj z9>SEpvj0sLP8Cl~&s08(CP-OLH25_re47kb8j><4u706ksckCeyL!)&eyF+y z3?hMHd<&Ep&|LBvf0EJQM6` zA6`211!nc>$~#0iJ>+9^ahi#QDk=hTTAp06_;?Q!h`SjR+IOx%`EG4Jz=!fmuZeQx zNOIW^gbjDaL~NH-2)D$$Hq-cnRb4Nh^8yXLg~V1F)hOylOz+;(<# zEIYU+@f@@=nzzAieKCb&!VxVO5W3j~^r`r5v%pGRF50tRWVrXqO@z|iJ!l|vjCWwq z#9eL2qxJAPq%zA?_q+pbYrh;*p@{mh8xj@<&^N{56M5R+t4iR>V}*HEf3>-1m)d+P zh+b-w_@@~{NGnL9i!jfCY^_S*9LeNsY1*p`SJgYF_6(MeI1IQEGPJ^r{`Q2jJ(3v| zwwFL3Lh*J?1@mBGxV1WPSZxA8l;sm%5`jVADkavo>OG!P_WKwR#e~Gaj1bwf;GsBp zmzZn!eqPK~*8C9f7`-epKNbucsZu$(BH&_TgNFmtQt{u7cOc&F9|FFw+>Gkw*gYH~ z=?TlCSof8rY4NNWvsBUpNkbD9M;M7DV{-4s;9MF6H)|Zp&@z9qny&v>^Wpzfc9Ud* z!{q6%z72~E|EZ%=mAR%RpK-!Tq@lQCBRndS3oa^*X8O`lPM%!(BviR~C5~eV@}L1G zw(W5rb}pHkuU0!pcyd8EW^jopzcwu@REeS9vR?x?M!y9RctXyE(&&*-FUsy!&s))s zv9>*XD%W8#*~cnEnXU7i?d-yubSQTOR_HnBVwD8VOzuB;|dC% zIfvh!LqR4gY<03Va`Ns$Oqo&(;BI*-pP={k5nD26exz}h3^8iIqTP#|)R6b-@cXV9 zV$C9mJ~1ewme-iVBDgEPPf3Hh1Ya2wjv187eO7oIOe97GiX?T3x=R z!_$%56n6ad9Ov*u=56T*Nwkk(CLyRt#l!9*b__L$K6b_}1>8&#*{qm@vv zUmoeoiLKkiawg+3uA(El!O^+z!^WY5i^|W<6&;#`+FF9;U)5{k>&Ywv;bY-4X+8b* z9;Khzt6$dPu8P`SKo z^O7nhW9V_Qj-UumR zEp#eWu%8dk%dUWiwlamRwqPl3r`mcZrO*2IZMWD@{bj97IY0=E(jhHf2V-4l2K&H)iAlu9X#S~VvQ=paKWD84w3rIw5B|N zAWv-~mHnXyu zxHor|N3@wd{X|O^ADjTU8l!v7dzU?uni|<5o~a$eY55~NI~@)cheaxQOLJy?2?Q4w) z&5oTO81;%P6w^T#5*SyypC1fe$T|ryWWBd_1qi2)$Oe583pj z_`SYrL-@EA-!68CXEUGS=xmBFQ$4S6U#N5}1p>2Gi~4EHzciLz**$v7;UP{qa^G7t z^7LqSlV6!OtA5b-hq_3#*`_plgyOuhK>1+i(;?Yy$83U|30uIFI9+uj8Ck7-Vx-a|v&*1Jw>nF6{#fo0`$3AcKTUO{_phQ_yF?w9 z`R|ID-;07Lo>8|%{8<9Mb9PPr^=kX4A9KH`dh}9wtFjNNqi<3UFd)hW*Fa($7V;@a z&lg!^mt!&!=$l%-3I1sNk!4&4N3_O9D0p^FS1(A*)%a4tGph?$Cbc>O)-@=UvHx`~ zl9to5*#m#>yT5cB#DJUWhl8TEP!?vH(?oMjiMGfI-2Loh5(R9h2rWDyt;*2<>g@Hp z!;s-1O3X17Ugo{YSCog3YEe>T=bj?gVp3#!lNS!Ht;K~>X7#AUMMC#2$w!8=gAw7p z9z0b~qV;+E6~p^f5?lreGvvP>nzDnhxC)%*?u^U4e-a(81ivEY$;fq$IDF)h>9Nal z7qdaS&9gkk$GkE=hm9F?XQ0m9j1O?S*wDK-Kq-M3dK?qdjZ~B${t`#?!Q<8$`5*Pp zJhS0$CW1@Z{kn9?Gfu!z3h*>waVt$tmv3F(czlrnP|68~&h5(EN6C9_r|;cZM)Qq| z!2LF4q=t>>@zAIIZaA_Ex)eIK*x=etG%^5qUKYwi ziMzgY35qMvYNYMN>T~UU$FSskUZfHA_hs+67t88&NBt=k05OPqDrgcRM2bi2UD2lN zo^@mfH6ovUs3xvBS~UG5rnx(PLtP4|6h8cHQsQ}MnPc$9YaVBCMDpr*B%84e0k%m1 z&+R;2K2%ivO>;b{9w&z?_QlO9m{8rOxJcmJnK3T`b>5%N7IhIS60uMIbEUSQXgJm} zO?R~Q!$WpvsLSoGy;H$~I6)tTv#>|RH=WoxncC^hkfnK{F5zgnIjRo&32fm!MiDavbd7DAbptLB}Z%C!W{ z4CxZvj?!YbA|dKJmTi7a&4juW8{~bOx$Msh(j&1P!LvThf*5i+@oQ?BBd%?#w}O3| zy%jF3TjV>_w@pFhCoLza#6>MdS&&y=6CMiHqM(gEW4gYLT2eWs-tvGjt#e;NHxOqj zp40R%?AAp3*EUndt7vVZPnz8cs&^R}@};QahRN1{yFqf9I1=S|ynY4vc9w(Y)qADD zs!aVyjfKXOf!{0>g^L(BdFXOHO%8mfWbtCtL~V|RgsCJp6`Y!u*+C3LBug#+%MqqQ z7fV32kxIhpl2nPI$Vmp*c=fw{-3&P`-}G#LW4xzB22F;gC;Cin(x1yf9ND{kAKZh& zdfRXgU3Ic-&%|+lpN8G<1b?CGJF?zA!r>Fj0+{o@712LFgAY}8lta`&xnaF-_ebu> zG`%zn@)dmGarJn|zvEy{uAbO2)DBTM;CBb!?P~S&YbJo9F53)Zdqr@vul-GB;xk^K z>K9_C&BJB329^m4W%IrXU)6LXhB^%Co9>|*&T^)StDmBSxeobuLkk!{$Xb`}SiP1+DD<|h+hn(l7Hg%35Rl0SL~ zPwAW2G%k-llct{2BS2akq;mjPNK}p)LHX8`Q~nm>SbcHT-rEFy@k(e)JS4<+c*@|x ze^)a0Up?1lO_K15^aIY1AXqE}r|55F-z88YSEw4pv!V1I-zIvM*>)p?U`%1@`-HHX zKJJC+iX=)VZ;7TT6g48>?2o_25(?-S3mM<59|O&X;>0J%0~?ybcRJY~SgD-$(q%%Ac1ZLMB=9;uQ> zrKPL(p=bJOQ&rVHNP2co4a?PFD&sacpAEg82#ogqYOr;+Is+S0>P`QYm^4WlrBf zwQ}pdflL{=kxE|l-8>eyB2Yis;cMY!-=KlW;>Gt#)9Ct=#wG99t6O2#47`U0;&_Vz z60l6ZHSaS4bfs?R#)#c(_Nc7bJ7c*M11>s^rfEY9)?u4}-{bMjQrhXUv}pHy3EPA| zB;|^ydO`@M-`nl6<3oOxK8KM57x49EBqUwd?_TXMr4$v}o32{lxV!I133O0BEv|=; zO*)kn=}}I>)vMk-3E8_`%a>3N_8eK?j=>GDjY}*(q*RdT!~)(zh>9kwVYB+iDj~Yk z9lhCf`!j}s`$fMRa0w_KOv$~Fy$ctp9r4N+G${I=$KS#Ql_^JbLrDf5c1_EdxEwU)NkxOJxBU>yx1 zVhhDbv&H#3OqW|eFJ`$ua&1Mfy?KX~e>uymE)uw!{k9JvmS=9MNSQp3GYF2Jve}ORb zx31ODhubtMMOY23B``VZbp8F#aW6G%9H%$af5O&(JyxtL-bxMe5)HUdQIY)Qu3o(S z(*Z!XGp4%KBS{faQU@7Ue~Bj&=AA1yA|~pkA<-D3|H{ftc2PH9?s>A6o%u7b?|8uf z;{KI1uD1l<)?*gmX!YD9g}LpZ?25!TJLQ!j99+>%nh-d9p}2ORa1%+q7B~!OiR;x`f4Nl{>A=P7BcrhnCXMsKh{NJLf#v|>Z7N`|pp)KI@6JH# zxf724grvqD=haa^;IW|o)LT1C7EFjDPJNuGg!ro)V;1HZPdEm2dwGLb$YdQegm24Z zCDRq3r1ijK7~9%fBb{n|pKAEFynOPx*_wE7tII*!g<@!N%_cqQg<}5Sj>?O!H~^1! zY}@k5xeMqH?X>oD89v-;oiqty z%KG%LoCP%LfxNsd2C)imRCwEJ)M-p?Oxl0El;&xNE3~wd#%rd zFm%dZYMri}GmY-FFr`2Xl@Kn}ziFsSZ3Xx-F0{MK(yemx_+FD96SRRP zCcp(~G0o=t?ef5vzLSp+bR~?kAb5|Hy-+btI1*u3v`Ej~>?Il6FmF!2Rs7U8>a-># zJ5xM7K#7@|2LJ6AUyfG(q&$ON1C_|wGKH7UQzBSnM3}U!3pI+uhWt}0hm6bTt;n>Z zlU=n3(g^2tM*NQenEmU-ig)qVGZCFkf*ceZLxq~xwHklR)Y+9Qtn9vmkwHLSP=~g;@7E&c=-;iRSA-+Hxzx7n+#X=j@+doc=6zKm{>hyxi6I})0 zrN%cH%wDv!r4>0Kw;&W?$Z7){b`eq%ay=8Gl!kYN)uvtX;Q2nwc>3HSE>kLAsr8k< zmF-rq~pXp69Q%OyoK7k9+0EWVr14* zrvA{VC4FJgaWVXD#2jm^0v9BWE7O#&b+AS9WL;8vIZP((ix+~V*}>qn%3*n`i?6KD zTVF{=rJj+}hGtM-f)8Pr+z`U7aU7i5|zt)PyNCijtAoc>+m@L zCM54I+~g-C<$R9(X}6>?<8;|A7eCc50pz@PcXs{lCCPr&jYgR2yYthPHHfV1Z??TgXp&Zb660Jl&X?s;_n9H!{-F6^*gI571_$absr3 z4nenvxc9QD9+T0lz{~0%qRbtuDv87QKNgRki@Tw8ia1m%OfM(IGZQ68e=#$gi-5Q1 zCu0z=^pWavPQvu6H|Ae@XaT-H@d~^|V{Xlgm zJyU|kd}g%b0rBSP*ZZky z8A-J^zlsMIn=pb!RWVDF#8KJqqAD{DA^=9DU>Y9Qn?!*sgIkQ7<~Nk!gSq~#9s!Iti|K0;ZY?g>oxHEbn> z&X{Eu`nge5(KTpgeeuF5AJc|~Jvb@|9dJPI(K>c0|!98N-sGjCyN+7;k?O9v4B*BLuZUzuE3<(f5Lr zIvmZ;Jsq;*(&6wJ2RpFbg;+M9m+jS`%4j$I%NC^hx`LVL-3~|+WYeD83T^I%KkMv4 zeOfsEYV?EmREU5vE_)A{5Qsr-^^lIAGQyp9WwoyyrZaWAsEa)Jlwf9-hePvS{r4$$ zy{&FT+vF)nx^X=7eBN1%pHv#Oc?VlQnniVuS!FNyP5;#{6s*(Gv92*5%#6H``rA9! zTWAEfDi`BAw04eG{@P5&{EeAOB~>;a-AnR9_7(agYxQlQ25r=z{OxEcWQ>v?T4ghb zlSL8_@)GVR8or;~#L}U9_3r%%|%$ti120M(Z62$J*=} zQIi!JY0fMOp3I!5oOGk9MoX>9t$#P)s#&LQ^1Nb~%cH3oC^~9(ld}C?J{QvP0r0OF zFY!w0Pbx%*X!b(?cnX*Mi8|T#Mf@OxP1N6k>6Xv|VnE5P3V$cH4M4-I@Ax~ZdNSRg z3t>#vt#_iWhGYm^)uy#OP?Am?K4&m9rNod^4(-@W6}{wzxQ}iXv<$NknMg;{!uCfE ziQJ|HXP15AHK$jGY(sc+b_xxG!q1L{!0!G zN+OWSe#9qZ!jq-PmLg$c^m5TAahBvFXR#R_+(u9M8r>T|{uV;Ksl=TfV`gyV78Lr_ zM7>z$aHopFmPlGp<52QVp$>ul{dLc#7To0Ni2x{h?Q>S-Qg}O!$UGaM{qd~-8MJ?J zJ@n&%v!q9Q4Ie>k>$$>H`gwh$fZLYL75|Mr|DRJE_Pa&gX#6O+aPD8ytt$Oi3wTE_> zz#JTngKj0nl?zkNftx8CPkHLw$#cyX?)+u`22{*lp1xm#N`6T^NfQT zsGaT^%dBr<2D0;ek{7jn~iiD-O;PG17P^7t*$iw!B8`*6O*c0}lG={1d+T)Jy^+kc+D_x{TBv)Itkq{iH4!4*W?FsTc@Vme_+hsqoUjDJc)CF?5 z!u%424MWzUN)BIWQR&X6imwT_nqOp+RQii2Q*~ZwHlx>Jp)0lw*P}%5OIh@{d`sj$ zv9%^fm_bY`$L^9BhHfB6$rWk#&)0Gk1upewzp@ULe5iRDXxghYjC20JfL*{!L6J4S6J4z;w(|p=LX#@AkXJLretaP8 zNk3WgqSXD;@%Agpzb zbJJIOn6r0M%HO!tiWtJXPnSrJASwfwvCU8da3DeZq%qD+qEz@(Ex0&^2mHyU0!hj}! zbdZM5dRy>&F@+tk?H*D*uErIf0Yd1 zp5R+SV`VdXXgS*D;zpLwe%IVR#f%fEX**4;OPHpU$on;?$mtAgWw^BVg1jy`7xv~b zz#fAs)^<^7ALp5?%<{vrpx;5$=)#IqxhZd;O!t47d ze1acJ_Czp2bFE)f{AT!uL7fOm;h<9|>;b5W|0yIdOI~sHC%5UHllyee8HTiPWcokT zNq{L(>R-#om|y1-mhn=pc$`YLLJ0gmUvdAf>;$aM@1Ck|5g%dg(x%Z2eDkdTdY6Ba zFo`WIYs|s{Wk67_;Xwf-ODiI{gk&&dvQDO9>-*B zN4eQt)WH@mGycc&wRlWDNQV+{h@A0WQQw+Gfs*3NEo{wE2f+qpTvf#bUvs<(4KkkB z)-O<>KjHLck8ihlm;Y(xcNS2%fd>}~y`MQeFVK?P=34nHNOID+@mc3mcp;|XNIWgO=gEFr`q^Xa=w%9YflpR=0pRUr}e5u%0gQ zE7gVgaN6C%u(0`HBr@7gXJjG&{4ls@H`e8gm*kLZu@wut9;1@=rD0SGk?2bID?ZPx zFk&U&>e3K5nis06^;||I2nmp;kUKJ*rIa-$TIN)!GOFcsD4fZHMf)~6o%kLtSQ*PLbQ=F5g3gHn4O8;X z-eO)Kx!=-jMQ3$6JS4T*m3sjBM1nrwDu?pqVZrc4dEetzR#WvKsY?thol`=2N58<8@TBlJgXiolHY<(Yq*U7*$i0pxT{C2GXOZ`K;o)Hp6N{V%(HL&N6zU0zOnqkZym{fM=M0a8{YgHK zZTmKnM^!RV*y}#-G_J8ponyd%^%I{~hYo;i(d&~6zJJkl&HJFnIOjxHXTfy)?RVN%ms3>z77K$luQw zv-g2b5A@Vys%7_(+l-g(@zxsvS$B(|yMfG1>bg*T-~}j)&vx3zX z@JFQHDpZweW8YN~L(4haP7BF9WG}tIgj?BtoXq$cKIl;)ZT(H!%;CgHh?~<|XrB9ODiOl->YngyQ-~45vr6{wK*&myRm;*AhOY2Os zgRdUM@93PRd9*-hhyxI{-(Wk?H!;MXS>^W}-pUg_@MM0VOIWiBl~~^HkP8G;2?|Go zPzWuCHV4~f!7N!fdK9gOUuBkjrjp{F)Mt5x1RT=h?i6>=?Nig2Ecjb#Q05Et*j#pv z&mhoj@DXK-Ne?3MU*(M?t&LH)?8)V$hOAf6*yFVQRGEN_3OoFw6bjP%$rrwd*l2-- zRqFdKUHQKTJ&HT2~i3eexGyJ%Sf(d3UR>b?PJjhQX|zj~^n5AV>B$2{gJLs`bM6uLxTa3zN+A z%d9T2zGA-evKB{l9-~L9yha)?{e+~X^Y+5;fGcgT<1^s2xUW%fTb{x9>+ilgY<@2l za5yha8W-jxC+j(V#g1;bWWeA;@V94MaUn2fW|l|xjh6TCwtty~ZDVyGOyQduT6GHX zN+KIB_azY~;Jkx#NzYrfxS5|N^KZ#&+veOT2tI= z6^xTTp#oQD(A{t z?$TK^9zbn0ElJ}j)-3J&a+$u!&?r60kl~$(7(})vD0wnbqV~QX#|=|smzd=6AkBg6 zf>d#PJ5Zhk+yWhJv(hUoF+;rt;8-j`v8tXtC)iY^;c(%RL*Vcs$6=!yQ_2_6riIz^KwL8GKXo89qJYKhu zNzaJrD1r71H0f~%vLzW*Es`7>_Cu^{r?Gqu*VWoo4Ws1RS@I*XqvDcY^sc_?w3eXo zu#X^$m03Q<&^I_+wnQUqlxvSpO4@nC-Nugn3tY~`Vs_aKMoc(!LIvihaUspNUTyCX z@!C?JMm#vv2fq5abIoMFnjcJ4 zEj(!2EU>fIC*FFKRHh+}hS{!TsF7)kqN0CPruqHu%h-{w9XLx_(I3@Fs9bAt$2fp0 zPrvolmeSRZlMR8kbSEEvN+R&u_bH!rrgzf0R+$r?9gkpUW8~wW+UAak#hE7crbx8>m9(|aV7BdG!3Cmw z*5@X9?$#EU@8{HP)OnO`DwsQ|N(Mvwa<4vzjQYho6&olrR1CG#Gml$;$a0EHibrB< zUYhReTq~p}#L0VUClBXIZi3$@48;~~M_)rWfTPjAac^d(+S%&$(g~Bv(Z8aosGd0^ zG-#seyjDs(ex8%#tX{Ix-^hc;wo?sLH*&6tZusC|x0^gDJC)rOmMKzayj2|2ke{Zh zE89DI@S;fNXMB%jGlid}7cKO{i=kFZVVZB-0iXOLTM2{4JzXFzrD2p(YLY~%j7AukeUIVZ8r_*I0jC2cZ zQ}Q~{3G)c1+c`qJ^?@mMYe}$xL+9?EJL2Tx-%lwVYk_tn20l6VP3@tSpY+o zBaxgOO|FM4=r&*Ojc&_Z~6RAn>0?A;ABfCF;(-mBC_ zqO-SInH0Ycw~Q+0J(ILz9<;};`K6F*HMwN@JE8LRbAC-N5|kgyp+{KQN5LWq2VvEi zxh`2_z&dUqa5eQvQ?e9PU+)|@jF>5S>1yx2TAbY-9u~I9%GCSR;t`MHObwgNR_MxH zc8WD^%s*vNM0K_QK~RAJTk z?y<3O2v%~C(?IHTJQ5tH>iLhC_|@oGlamCW@hGoRX{Ox)X zg;cQ9mvF?>p)}OBwf!H{qfBAJcsbR#+lvM*@x!Z-`lWbc4Ux@!`J&evfuk#5<=z^n z-PYA&9CsMHMwaybrY`am2mSJBYxE9#6;%oWc5l+9Rlg$?x@2dZ`Ttx$Rv@AHUA%*r z-ek*ub3q;HGF^-xpCuY&@kV(|bexW?x7nU$IUNeA^u(!q zN+N6AGiA>^L^2`H%iH3zQ8ge;B2Yy?GvjO+>sv1kpq&Z3n_ZT*#`9)a0c!QeGmIf$ zPr5>FC^P8bWB6pB{d~1;&uhAQfnmdd`uIqC92*&uqA0ogiTr*KH#JD49{601hKo~Z zSjP3c(pRA6ETd$n!L2HnhT{V80K~9z7O746#rCa;$b`;#nMFum~T}Av_A} z4Gc4$v;N^u-)McQT}x|US(2$~oGknJ0d~q-+H%j@wnzT=IeNttvAMnPY4=_G6nic` z=;#i2zrVBo`~9``>-6jELXq%O=?q5(v5;O_wU|zeQc9qR6ja98sEMR`IG&5EDte1+ z(z`Wc^oO65tPxgR$&=W2?bCI+lsK+qNn+^q|f$Suu@hQ8tA8+Af_6#wM_8ku=hb!(kJv1s;dIhk4i3@K-O56Qm4~#ruJT&%7fU>S-4wn2F zz<0Qvf0-S@fnJkA{kmV|5G`Rc#5K-D?G}w0YoP!dlv&fuUBs0le_kt_BhA`uz=%`A z=1$8kVD+4F`?;?l<#ef>8W{;tLw1s!L_V9rpcGIdgKT4gjMKaki|(|n#?DwJaMFBQ z(P|BXAnsWmkDC52SsP`k;1cThu4Q5+PooM3KmP*ttH)b5<|m$<3EtV`EZdIsJ@aXe=}4{7W%t#P() zwHLx1Z;xJZrlFqh$@ecQy{A9&aVqgMM^4>4IN2F@bx<;-h+G6cmNuL5ZZsHZ`W8e8 zQCid!pDt3CExT2Fn)t9rlZ63$h9ash*i`r>T30|6xJPb9Vmb~@1MDmx!h;WzRZWyu z_=msk`1*Cu?0%6`nr|cKJI1{}F*HaRvF@tdT$w{^qDYbC{f~7`{8z7^ z@u&^NG*vT@wyt&M_u~AWcV`C%ocYTb!!WqQ))~t%BvZ+36#0aY^Lt|) zSf8p^vgpmH?fg&M>zRiIT)H`CE4nQsa8FYukldmRAM~y22U`1>Q9+f14#jkcQpV`q z9Da!m)nE56mDTmQD3rbhmoc53B)Bk#<;$y)d zSo2DrpJ;lU_2B3;+C?X_w5Ut` zukt;ms(j7N zGS5E$^(!Ib_t;U)^+5?aqhZbCwd4xz65F@NIcu)P5enL=n!(Dm*)c(;GUxjnMe~Pba{) z)%EcI83PqEH=v7bRZdi9c2qD*iQWsa?O%PwD49*^B!EElMD+$#4Fqj{9TUmq6%qPP zy4Z7X^G~G9uhx;MOS(2&#i2e^4JYvzlk>nmc{!~k;N<3vw;fc)@%O32I~=RD83C&` zo1rXu8Z@daVe2c=Mo{wgL)QoW!?@XIp2Mqokpg7L3)LBJv$6!_m%)>)2Fafwj|`6n z;2@$>MVPYntCVs5p*l7vvP~iF?J6W#)il~y7RBSt5 zY2wIT0pwP{z_9hA4YL7wI(K-p|gZ4>L9*8_7l3n8vQz-t)I)>0X5a zXJ`h_R2%FQ%za1cvoAu#cD-fK-h@8xu~)owLSU|nha02@j+RZ6GG1mPA{4s>AN@#k z+muFJ%eotqS)PZBZ9BPw|Fp{j)DF`3w7Y?$?wIF7%}EZa_uHJDtpw+?OKnhn)mbU( zmJH!LJ+q>00iGvq6|RWvWyY?fEH;Fb7viDUVek^=n(VCD^=@Dbs3|ua z3hOrtm=pVa^c731inosX>;0pqe3u_2`xMFkl?OuiWjyg zD9d~n!#WbDh#u^0GjRhbQsKKzA@Q!619JA|i0Y}nyI~z6syzDW!<3t7ZePuBY9D$) z63kB&tWu=Uu7;9tE)5>-;3cuB^Lkr3S)ozn*Oa?S)cPx33bcSnjrmJ43J|n-H{PodW*0F|AQ|7!=yS1Og2WjBs~0*QX5k=kOQeqQ#f7_I-&69dO3+ zo}Xq$XRF9ezQ8PM^#>O=81kkVGLIrJ)2I>9?$x@$F@TRv%-EeKY(tb&o8#0MOP5^q zOWyh~vgQb!9noNTtoBo$YczWx@R;`~8`+m9xjmKJ-;T3{i5Qm1fTXpzA(?lsK8Cbe zJ6ciH-#dJ`@7gB;wLZW%`?w7(`(uz?Dzg=jE-uYr-6RMPgI%t{gN`Le<0y}xKSW?H zM{*Rh6v3Q=r)_8MJY)9mDZy+e57-lx9GCeS7T;qw$B$Q5|M_sd=_NLP@2-ob?`Y+A{4Sr z*BlAAJ3U>xFP*OnbmY>6oz-X$Gu*r*iH@BJ*$Qy8n|pLnp0L69Q891wx!>EJ6!bG4 z`9>M~j*~V@0zS!WmFx)b3Yo_QiHaHFM)=8_{mbOg!Qls9>b@Z6e zNsSt3YyF|cuXl$GM<#P-xl7X~+IB$#D8XmYO|;xGz#UD>0HRF_)DndS5q= zF|n(+Aa_M&ue&kyDZrh$!-A#7#BIPEOXy%me{E_Hd*h;Cq47+d0Lcs^4PB>$?e61TgJ&sYEW z;D&C5UPSFBPu?d@ZKDp%pF%38Eo50YWqULRTfVnHS*PJvOfB%g5f`h@tp*JZGpL%ST~5)|3{fi9B3=1s?uLVQkX)T;&;3Ys3Cx3|;WsZ(ivh|J0vTRs zIt2J9ney4|xEuM(O9N}PI5gDPl6I6XtESqE>~xkDP97u1tj6osB@_5Bt(C}?%@{KY zHt8nX7X~lJr;TuX%c&_HE;9wH@R+t_ah8QR;u=6yLg>JlD{X;<)IcZur+6nzH+nhDaoQT*NO%`za3)OPx$>nYLhO)d}s*{Q| zt&+5pa>MpDf-b;qR*DSWe94DF=zP ze$llc)l;PEEcJ=@$3A+(Sf!xDhl3~2JbH|sA7_-|*5;X>NFg16el*Cch!db|-cPt# zy;>cRG_gz&SW)L368xgeTtkoxM9Hyo>_J}}s*fhOiztn0-#&yHt{&qQXZcyA-9`sY?}Sp;i8cpYVh7^DmC88NrHJve0b` z7AhKOd|z3^EoFpVtF zR!kK+2X6-n6uB|omsb6$Vq|3{Z;(42%dRM)*Gr1D5nZ}*Vd7aVAHt6wQ4PXv(@q|p+)j)`b}>4`&fUm<<#h;C<#Yt zh32PrOZ+x90&0I2*?B2jxTb?&*-tHOg_Tt22k7O>%UMVF%uAyy`dMAWn(xy-gO1fg zX=8}jUmMWm`Mka7zh_GrOC-@?qHObsUi=YX{BJ;6qi`w@p!C%Srpe6%tjK2LG!LmUS zzfLsDd{Bp|=1z?5wAV+V#{ z2N>5yB@y|7>u&d(iTfd$Q>mM50I7;!A6tQjuH2D$PM8jB*iqZx>=OO(in`OD;|(Q@@#afb_H zJW4)|PvYBo=k*GV7bF>@i4IG2+JN5k%q$Au#8t@mzaQdS{fPFh_Zyi}_CmwaCJq%6@Vbvj2}{ zONbQHZi0lh@&3(>%Iw~2 z36euOOIm(;N3_2)b0g5Q;oQgG%mJ%&%hM!&H}`DhP0-@_vBz%^RjBe&arCF~Q;AX6 zFM9*q_VXwz!nb?rKJ0)15H-h8e>h^CeASqc4Z|~`K8#5$>GiUPByWdnvoZEoOuBmHVX>0+OZP5b)YJrT{;7V+ z8Ww~@rnLESW~*~JA#5pG2l=#0zC(Wmf_c1+Bhj^^)dmyAv;NZS+gGiN>gs4;7Mg8d zE>alytu%1PVqC~%gsoX;F@3x~OWZ}SwRpplTNJ3>RkaK+S>Lk|R&{&xqMl-|$!8op z0g?u1Pv@6lCJxxc4=uxuZtD=E2yo>;v?#7fI}tAX_;7uHV^*XAYC05jv`)7VIn;i5 zRNkiL z$kw3vPG3~0&l%6nIZr!TV(B4j<(9f^*4#}@c(9(F`4zd(A^c5yWNl+jKCvx%2-pGc zV&J$>V@$F^!YA9UoFA6l?NJKuN>Ce=czGJhI0qbItRCF&cd0Vi>>#Qq{@t<^>nM=I z7^*I;d?Q1S&MNgX zT#jn!T<9lv2ZEdx4`aJO7(K>}*s+X*Cw7mAgv?cfR(+DYmy(mPW7;M(6I8vxtZ%uu zJa~pUqD`MW@8NDO$#06rI_>YDhvgD-XwQ92^D}3W(Sj=X4b%LwEs#>S2lX)@U00|7 z-sPP@|HaWp_KocIan`l^2iDTtPz(B31Uv99lWeDAfs}~6+sKXoS#FY;LjFN<_}_!p zdUzYZF(7nqte5!HsKK}NM^>7jf%BlOV>eHwimMRGw_M2CeBjXdxaguJpk|zu=CPXc z_Y4sJk9Vs_r?;0IhGkuyYjp$tLeXvgilDHchdXu?{HTh z1{!IQt~>_rL|jx9p4d+LFl#L*8w*Tn+)ZHNvc9U2i%~5&2Ux+-IB69mSYR}B_-qROSNJ8!E2Y`}kU2HJ#eLCx9y3iCv6e(wVvOVE=I^%|wxKmT;J&!>j!=jwnu{%>6 zy`aa*Mm1scrm*hht>QPWq1jp9J8Az9UPeYp1FxOmLn9;1p-^c+VY{*u09m|8-YJEf z^?qTw`{i+=TPGlV@78q9qR$T~@B1>XA>s94VPPd@8e4@9g)HZ_BWUUrzl!KdJ+y#eu6v;yv#vQ_YX93ahtEISJv+641xcE)krJKvWq|aPB zUAQ9C41jk2(BPnEudB!9PG$F9TocdHRhH-t5-zHXvFy2XqFR!NBCj!Fw-KI(JTt~mdg%#6xp)e78Fd*OmO0op&UOEw)pMn1fDu_q5A^n`FOkJNlo`PKuln|`(P&57srlW9C;l=V+Ks0 zm1LpN3fn1Gd!H@+m7<%?qGfgXMf}xSyHw&G(ZCLM&_-3>})VH+SU zzvoSO06z#f`s2F?zrDQvQCRatvi5v6_4@A*oy+>Y%fP@uUoh1%z5BfXA4dSDun>-D z09XdMamu_0{ZhBy4Zu%gUe*<5j9T8c0`uZ6fEFn59UUHCYF~1=dzTXt``PVq#BB?) z`m0JeH@C|Jchp5Xz|#@&GEluV>&Z8 z0I=W;w7553(tPSOcMC|kn;!+192M;O?0MBA&h#toe(j4m3$ZeEfnzM$BB0Ii`YnzvQd zFx#;D#ky_iQ8JEu(U9o6{U)6HJ^JhFy}K8pZ9f3C z@Aa>3dcO$O+fMn)%ZKb;HueY0bB&#bWMJOi-#4c~;L!m-l!)E*`sGdL!4?2nA)qk_ zXgPP!kVL|JZ9k$uYF%gX6PY7@PO47ksvNQbR6+G}oU+{X-W~k_V9(q+4j2qZWpHxB zgKefNRF%HPrMb;|{O$jenreEm*a~vYM+QkVj?WGafx^l85&^Y!K({nkHFX(qu%IQ! zpJ~Z96Q#0+)vHt~QtF#v(JTe(@ zYiC#2sI96@4TV0jwKOY~Nhgt|jm;;YsJ78x`YcJ^oq$)qId;s^;<&>m;5%Zjw7|;6 zj)8z!^7HL)CE(pz3tlNnUQYCXf2vn-__nR<>smb!6T2fQ1-~D3edcOKLng{ChqpN0 zsfS+f#9iwFy8PjMAbwNw-FF!dWMTj?F{pkcDxc05qR1LgFjc`*zt?Qu48MtP zUxJD6lIj>RN&)1BWx$)_!ujgYj&)vXCd3Cd;K|tNy_q+M#X9^AQ(^azh!2=yo2pf`U~9A?$4umQAtxeZae zfYD3+aS(f>28l9Q>-Rk=bL?bE>KOW_{0#_(HFdv!sX`yNaTu~mTA-+vk)Ave$5lYs z002tWRw&?wfP|O?ymr*vHh`VNOcmJ$B;>n1xfs3E`ZB4!{I9mPg91SZkafEEo*6E+@%^5`^eJ?CaY-_&@h?1?;FW}nWJpjyj!Kajoy zKnro3r@JH~5G}_1)pzOgj?VzxP`%$)pPgM?I=PBaAb=esL9+$$nux|+R=T)~5`?Tr zJI;YJpr>D3j9=lKmgDvDSog2WSxz1v9s$!XlJmQ0TH&*9e=nSjCk_aIN_W7HJH8c< zi;IinT?zzjb@}^`LZVoi>n$J}CEVeNW`Qix4P;+^y)rY^<096sP(^L+`111d4xlQd zwY0ZSnyGc`2GC80Grr3U7lpOEakYE(`T*0!<|@byaId&dle^^g8OYE;qNdRPudid_ zqpn@e2J3m7NIfIqbU@IS^8g4)qO8?MKsNE-)JDds1Igyjkl{Dy0?(c?+(DA=d>Keo zH)95HQ%6cmwRhzfv3K9XzhF>+-!k1?j3^RTCQcwKjOjmMtX9Ca1M?pN2pDwIfj@9b%SXY(%(R$ONe zz|(n2=dnz9Zgjf^uLHi*!epEH4rm!*PPcdeOCR0tLs;;IIE0!rdcV5grw<7PmAQd| zc{q?V_w9kC^qq1V2<$HJZh^`vOA7E-DH^=XGV}hE27t(NUcX1Z$~1R+eMc)uq6W`3Yd z-a8XC>)BsAsJaEfAj7wd29+dmpAJ^oE=a) zlL}MVvTpPxV4fpLAk@-F%3Uk-)s4&n#ert`f&io+eOGQ=0#W*;d7*f2bad4SK$_f4 z{jr&VKA7BosJrv92Hlz z*`u|!dL~#uK(tYX15wVGn+!d7z3X;aS6BDf#~ngt8-eFZw!O85mTkG6+4I%8-kvZ= z9`n_13rKxdI`1?Yl3I!oyaLR#w(S>KOt)TL?xC!vn){s}cmRcpDUhk+-;v(6L5b~F zZxz-qlQ*0NF}{3lNY9q;tfYBEa}IF0KtOqx!W^#%_(S9!F76O0znw~de7ido=~9dU zTBo{@_xmL;e@=Vt)!i+nZm!M`0Sl42L*}Tt{{9#GPAn7v#QnDfwa{9Q{_GtZ}S5PXuGH z)uESP1Az4)D|LF{=S~yIwY>@-6>u1w1bm#oIgVXO@;l^Cil8~&umFHOk%xgUkcg9) zEENB5@%Qa+@t0j#s0M}lUI(2j36KH!sZ>KN9-Lu^hjr+;iK->dUN1~gEMgy~pML>& zKW^Q}D0+~o&!I`F8=}Gfpd{9$MPP2aiSTCiG1}R*Y?U4c zh`ikXv_xP(c~q*|mS{W0P(R=FmtZW9N_JV}HdVrU_tR-Z?r4JU-%fJ+$#7VdO? zOo@T$6rDCMZH^@fVdT=4E@z7AA^%%5c}BbiXAWPowPwA%90p#UeVjV1UI8vr{D%1U z^Jl4@FAX^7`61C>X%jL`nvheCPm_J$#5x;+nKx0a5T;cKy*dj+Mr986;*9=q^X9gq zx_p05Z)4A&7kn+3wXRf`HgngUEw!%pjj$sZ83PV720VTDnJ+w^v&4khFzQL+6OSai z1tm$lq5-rHDCoMRprDmqAhxNWDlSsDzfBksA6W(0z9zZyeNuFJ&@n&%wFjU`sr<_T zY|m-zn%$Q^ z8Xh|%i?U3yf3U(#h+y?N;9>PrRNd2k?1me>{*`OhKThkD{_^KV+D@ip*2P+U63oi;G#-sOH z!_LwwQ26GUUnGV%D^s+xBC@`+(SQFY{*(MQlg)75t4?X%J{UJBZet_R{n~!)McUSe zU)A1cb4I(gNxXyRXbHOnexDlz2bHSUSz*|@HCky;emTAq|is%clT4Vnv^}fH*TM_47h=lq>AB?(1x;HX5;};;C zsp9i!g1x!gzh}O7_x2VX>84t!{@hSTFUizNkRq|0+xRp=92bF5MnON*0X{{-3yc$n z867N7JZThcjY}>C6TgUfPDC>VNqB&ob=bHB4n(uKA_bx4;p@G@FpMa5aRq^g ziA=g!QiG2jN~C{$biW_`>JaB_nVfw{Nv9Rm_Kl|Sr$*nx6G{-sj`H+_dVq$_@b_1^ zIq}DFxfQ}H^d*t7s;JKrV#K}i4Oh1evxir25zU0CJ`jj>s9Zb;H)`MNea=gh>(Ui0 zfW;I|V2CxBrym8*_1H85CTb4+Kod9wtQeWHVdn&Y2eYm9u=n-H<@De8JW>szLE4Nu zpBp0(un(8Q<*FfPX{QE8*KXpGhCf09phM<~nUndS`W_3(DAfU0X6`Ndbe(24Pg!oiH;Q}cPL>UXlh}%Q z|KdW*Exn$F)2&Wz8@<)A(24uoMvRBlWQWTe*)qwerhYeRZL<^r`-tEo3`HcY1`c-8 z68$4X968KP(};GY3eLd&+0|lwg7jG6P^1wSmpWZU7ylY>AYb$*(}^J>#3o-C3%Wpt zM2mqw(7_yTxbeR9E1A}4uy|%X$?MRUISqZCvsOuSlJ4v2OH9b2nX)2a=*1WA1B-!J zw4x8hu^do5?t&Q?|7mL>E*A~ymV#aQD=wRGu=W#2H9%eS8<7X`_>ULX@#IeVjV?YT zlM^02P!5o>tmZO#_(DxLip-Ti+}hDxQD(i=tlp*&Y3G#jfXL4?fuIfOAB7S8t~kGM zaC$zFq_Cy_RxcdIR=h&o{zQq5y$r0@cZwm+Hp(()r_Uav=ziUkf$ zb}nR8a*XGSOdFGhGRrBlO)xEM>W^QEJZ+vbNnFsRFG>~1T3jA-`f=N5)(gQQ2DXu3 zOH{6Wpnj!Ly!+^imd&_C9&4&zw*~FUAy~HJv>SCVo%?u;;#iF71J&Q!rcMbl`8ac{ zWo12@W&w%yMg_NBzj0dVEp+Wo4+RR&*5H3#oyxl87s5ny@`#<?{%BbzUlwkgN$sskwAsnqtQ4qKXKF3mUH^9S|8*1VOeFt z*RQ`FeK6Y<19uu7$%K6PT*_8!;%p1&;rOgf#7SRch&Jc;x1Boqie<$B^Q088JX9V} z!2cOw`^tRDNrlsYc77t#?9mQH!u*YZXzrVJaXOk7;XadmRSq%7z~s=!-Oe+3G%W`o z_wIZ5m1`|yeeUe+7S#NYEbQMpsh0!;$11}=i`pF8S+qwM2tVe!AL=cTB8j-H8DJQ8 zn!nf53ZV+25!jM5Hq)wr(tZirq^4q6g*bU|W|OqT+6ta_3#s>19+U~NtS<@pkVi^Y zd~F;%5wng&=)Z7^C6<$+No@>@V|;6(iyx$d)&vE!7APR%zT+zEl9yue?mr|_Ts$X} zuvvagT`9|~(q|RY-=7u2cku=}Tl%E7%)Q$~zD&sR1Z(3oht zl*in2{u-c2$&)3sU`#psDu$(=&X2q3Ztgc1HW`nAW7m*V#Gbq@%_(}r7g1S%1ZrV?3u(@Sy8B={MXY=( zA7qarjwP@|CP~YjC;k#W(JhBtQ}cde2F0n&JFV8UrXjPiX->oOGUNw!r(3q+s27b6 zi4FG9|G58fOjH}S%vh(NUr1T0xky@R!ip33WOG1C?8xTGIXmi?^u_qO4Od2-|J-avDz>8>A?P;3~4SgvLpZ<<7l$(&!bu+dA8n5o+NB?XtNm%syl zVW$m5SL)vvp99(?S_{68mTEO_{lUJl5jc7pGsi}Wvu`oJjQbTa3zVJ4g*ank* zAUsVpis&q;AX;ZUXJzr^qu&^_l4O*CWnXQL_>Ws&lHQge;y{+aCnX)tGGESU`wNBY z>ux9H8SqR8Qr~0KWexpyuW8(WCy^d>R z8cj66JebARrkqI!ul`*)DeUtz$Du3bE|k%bZ4cR6e7U*xk*Ifd+*)x~BqZ+fBgFRe z(*+;xIX}~cU_FiQgl8W?#W|qSg`9HXU9^LX==HB2YXg2ArRJAQY14uMN8P7VxHatBH%$$;3>A#EeBgNVP^uN#Y&k z3P}moOY!)h`hLgj=TC3lN>>FQo1}t-y;jHK9p!I2jI)=JHeAIK zu(F>pDy?;EPeaY0c?PLD1a_+I!(49U(3uXG&^nMElhK{ zUu8TdeRNBOVBWUc#i^9`pka^pe>e@wZI9WtKCB300QhwI%j8M*m_CKus zvQE}GEhtwwbAYD_+xt3r(x|zca@tbB*livPE64tH1GVjU^_132oT0)S()RPbtV9K? zKU>=ONx!g5ku5gF%;!Ngq1wEMgMJ7N%1~dt7^vcChUw@|F*w&#kRIJ3jQ-A#qfB?TXpKPG_<~i+^hHWWVg8hvTP1eA)cy*H03< znIgqE{CL^%JeIOvJ&MjIrAkt);Hx|Lb4Wbo1FNJwa>z+JBqiOrVVUbdc>ry?TB`Yb z!d45kw#_Z?&)>NCI&{0&GtzlY-;*Mb#I?ajbIe7muBMm}byKVhUmFk}QYMtSKP@#3 zllRH4#PLxHtQ$wBQsqm9chE`Vi>s%qjpQ}9q0&~z?WU@9#{B6JT&5>J8o-ls44w!K zzON2~WL$=;Z;Ndnusx_;eC@>CnmRzQ`4zpf*?L0AzebgcdWPMlugw5^lXykei+!Yz zKvc1y)G#nCh{B);dhBT}<^}#Vqosv}K8^>Tg4lWqDCfiwr}g*vtNR?iR*-*T0k+Qq6Oa#FmABnK@Qs|OC-s`FxZiuZQoYgr-M z9KXshaM<1h7U?rJc?^X=+JzSSCG0UATjPG|kX(KEVM}{us5Rm^5 zZmh>Bl~h3V;(_9rBaIbxWw=O|Tq}6b?t6eCL$V~=5teEsmG=oqDRo=$yNz$U9=@#uja ze-!SX<%zX;7)_)$?>(>Gz^kG5EiDB0-ntN8PVv=AYpxHykUQK6`uISiiXN>AfQUQcOP}QHi)Nl=tT*~3 z^L?fHm@dtDr6w$c7M@vS8CpP(mu!%ZTp$mEH{?=;BX{U})g{;dzK^EI%_J3$Q+Sa< zL^a&=itg;?H;Gp(dOgT}e$1tDy zJj!)%l1YU-_}om3BVs8n6>-&(_^`K{_@9bM|L4?Eak#{yXh^wa{i+Nnq}j-@Zc&g?H};u3wIq%#BdG z(zL+9BAK}pjv=$kGxu<}O3c|~vv$MTK5IuM$?f#C&u(GDd$^|Wv z&Vv4#wL3VaqOpVdL7+@Yq}gPvet85wHytUuba1kD9+Q@+k?}=5Juh?2ImQigfIt6A ztG7lIweR+^HnsKl22aQ}m}$+LfY4!_&1C6!cL`hI?ws#o))8sX!AjF>`(XFojrF4E zFY3!}y&Sg5H`T+{CH}HAQ8C(M&*{h846W~M{u*JA*Uc=iVejA5-4@JtmSe~#88(?UYA;Hgx|c2~mK$LB)tYJ!_X^yW@kjD*q2G|DzpMXSUUH5(q|!s(6= zfA@ z)NdA|fh{smVRo_-b+0t}CwWf@yD&}yk&;#kjbd`SG}KHjZ3{@lc|MW z<}e*1K>oHNYax9p(_7Y`nYj@vW!z(LY`?cjy1Hj~#n7V4W1-t+Hs}pja7ccNFvd#e ziBC2$8<5F937;DHO7d+v#FdFou<4Nmp+oIpT4HaeKLmbcGRF3#T4T*SoHd>*8rr5zQPG}lRE@Sgj{YQHWNGm?z0jDJ@iJFzBpbGKgp9Eu= z;f8eO4;=R;4Sd`k3c%QaRG4-O_Ew?j?xTZ0-<93wye-0%Bj&vss0Rmb1g_@*b9XpC2g#a!{ia z;r@VJQ#NEBeaf4mQ->vfx)-F10oHLj-4m!c@JPL%l!F&#vsmR@Q!wZndQg#B+VuK%uJurl~qFXV=p(7}7;5m|UX zK2OrK#xy`m>dOO%gmQ-!0jqG^A^)<%T4NIl!UGQeR|0LJGa6_Sr#H`Ay1C3>_K0t@ zC?`>wmhv_jG**PlYuf8@z{+ZKcJMHP_HfnpOI_6Ct%IR9a)#MC|BFsbr)QR`Q{WMF zD1xLEmq4HN$iD>!2o@APwAhXotAAC-P(nA`mK+cKeO$UTPa#SdG!?d`8Nkw4v6k%F zMsRM;efXTFLo*Aiq|z4pEo`K(u>ZmdaCYJGAIYD?0j_1YVxt|$ zO6L2%<`QLlFc#Q-$(ZCoTg}prTJUspYf3xoW925}&diFBHY5J}l5Dtw4fJ>mZqo!T zCd>^gh`6MnPjv!j^v)awu#`4P5@%bd2u~^uVhB+K_W8O-qRT9)ZVP%|Jy10f%oaT{ z!H+@cLBn#^%+lDSbevZCs2$*Z3fVp4-Y~EIHDX!ecT__+m*72;kF(g{VV}IIC0Wc( zW`x(J76L;igp-6el>2}~-X z;i=fRwU_)33|{i%{jehzwPkAl_6gkwd$+QAnPb1pVEMC!Tb=KVJdiZX0vpaQR}?+j zMp?yhk(T=R)Zqw|GEw-qxX3DuUZm;fbByK2U*YkTuYm@Nqu(}j=bSBk_VV^J8AP&E z<_lG^LUDU3W43d4Dw{gY(Z-n(K^NWmPR#c`kMI|L;t;9* z-o!!wsnr$RDsMA2L5bKeOa|sfpsb~Jz!z=Krf#vclj~d8Uurm2YZA|IXfA@%P`QP8ub6Qc9&sMwQaw^ zEkIOSL697zq`L-C7`j8L0i?S@7+R2qp*u!eZ|O!#q+3EdWau2ahS+QF{l5Eso_!q8 zKJE|Ok2tl~tU0f1UGe*$Ct_JjHhHt#V6(!S#G|7NvC9SF-^WW{9LyEf60E*4HaLT{ z>zPcn&%B}V)035uy}+JYH=fRqS>LwEs2iqTef<1beR%IBS84s1Zz=`9B#aY^@>bHQ z@rJu^lJaLowAyN?J?_+Woe+)2U|UV{j)yjo;@4pHSF?_PXb5O^-rvnUI|%C4OvN|W zedk_sU_~r;7wa(59IZs48#5byaHsa0>e=tPuNwwoI-UbzR8BPULut*@!lQ>?)ji&w zbezz;==Xdk@ZBuyVr{s~uYuI)j?95Yc_q1%<~tVN@o)Km+>rpmL0ta$jUhH`g^f=CSoF| z`19VY@vO6kGDaO0g|Yn+?m`t1g9qC*5la`VP~Prf%bf09CBs&p3%aRWJ-XqU*Q8~D z$0TLgx;b`0UY1AJ{l{;}05Y6&E$masR+**=x%6^YN+R4#7>tt*bNSLiEYzs$es?$x zZ^Id`W|;gD+(m`cNSiJG%=de`?El%oOG5Df4JL zqQWbh1LmzI@5YK&V3_DjYa(zH+G7;Q9?Qu8(foAnfD$s0Nnb1If))id4r_15KNBB% zZIPnO6xoc}tu7l9L|<*KKPf*OW%g#^UF@J`AHF>%g^r0yiDuS46*KL(KzhC-1E?zQ z9bW3yv!2yo1nRlY$u%ouvdY{N`yTk&0 z1p!#8lF55iLHzv*S#s?j--6HFPTC9a&DX`yN$6KNwTkTEQ0tPpX0 zjKY7NIgED#^B{K7)iu{H{*~jhocM@EimZzuts(vu-}*bBA(CM3ML)A3ZkMaD)C*@l zW}NA9FPk$q2i1aoa&Bd6JXVJr-V+m&~GU3=nU;2QM;e|?gO=)jlK=+!g5MMPK6$i(lu zdxy^|iUMQWj=a>wi{n~ow3x(YN&{SNjEp3@=7s966$!SE7hRTI@}dOU+UK-h)a^bg zMyVB)$2@(s(JiXOCFX}d%Uc|y^M7kS#gB**Pc61h=~&7nSb8Zg#i!cs`#8`vAS_H3 zsJHfsyUXIDE=CbDgO;y{JAM7ovx`zqrnA&xuDVV5RTjfk&fcaZYpaAry5FCoRd4TP zqg$FcYBsm?u4sa7#S|vU#=SNZzsi5&1!C-K{It)j+?Mq15_GIbB`VX?NQ$`?!AvE%$p# zM_KMA)?F5(HBT~q9u1Uw9SPMNhYd+yUQOtY4sJ> zHb(lq*d43z^*~XMKKq`{G-_?b6~o@HM3LX?zIl}uyJ=o-g@>vS+J(ARD0?YB@7~%M z3BLETGFo{G)kqL8!4&oVP#)$95G^t4A7WU>OBBwjPm&e7`I=LL3#=EqRNxFLMY$u5k{2s^Az|5OlJ}&aj^=YWjMr1?>Zsji=P#A45oQ)59lQMsGSY*iHPcc!Z?``4`7Q^wm+!xyZ2qw%xAP@Tz%;~3~)w5 z*BZW9F4oc@9t+sFt=}Pvvt4u*??7BXvbh#6!$PFUW|ug-mr#7Fj;q{R($r|_BG!3zG4%3 zHCXFP89oZv_l4lHR+ZbRHWBHcYfT;S2q<N)>+U?iDvtC2Foe)JD;r!ZV)RkEZrICTDcJr@Dd&Fi zwbfaLGUg_K39FdIFb7K6B4wLTFd5n+Q?jw$olNhKz>OpL5?bA4fO9Yt5q4~@7Wu-t zyd=Y9YG@a)-nX0p)gacK7$6BLWCK4&!YrF`k?S8&f%R37`TLTieRrZBmj#|53mO?G z!korL!dSf#p+YK0QfW6`Z%g&>IGd8dXF+S%+xy3z?Q1Ix`ob1E$hXbR;; zGk**R)EGydK=Ez{US~T$YbGzsNMXwR?Z-YO_&woI?SFcuFb}I(rB3#q`L>O$OeIiL z#`Y~;@i(x+#lnTeyU&wG&!15_G({X^QYvI9#nK zFReg_uSAWMoR8j_uYie#4x#3f^Uzl!{k5rD5XhS6w~m=bWCC4kRR(!@(mf@C z5c#b57xA3G_N7CBrCUWSp#bm6oIda6)gvSUZb-GK$YCN59b%F!EKmrbkuZzPNmC9p zdt}Sdo~)k}d|zSBJwm$twp!(l)Py0=LvPa4r3uCzqp_J^PaADH8MBFrtUr4VBZ9CS zKHlYvM9uytIN_x5G2$6bLGX6wwt#ibjDV!8F!OU7^~>P~ta$>SmJ z2%$4})W@kp+qlhkQ~YBSv2A?{I>Yi~w=jJ@<-FSY7=$@6sVV&HqkWC#9rW-8S*~$& z&fRTV6Gn#BP72RCFsb1_eb?$_di~Z3v7?;U;7Hta3c(jFX?7ks3umA;=-97-BU66~ zh9?CLeHBwm4vYmW54@Kio(4nl*OL^iS0EmR-gC^O=PDeLzL|r6G+Dwo70a5QI6MBh zI@m$%FJ$l+Q6W$C&&CAHsXTis+tU3Y<(YvudyrQldD!z0A4b>fHs*5CrL?7f|;$4bIqoTGeX zJnCd<41^ad-o73uB&PpBOc0Ls&t@lv^NjJ%tUlMmeR1E+C{I)bx9fm=$2%C6eZPL1 zX>=JGPksC73%9FWw;rx$JY`Bp>PwK4w0go?CAs84zU=r@;#zgt4V_H39y``9kTRGi z2#+f>fLSRzBPyfUZEYy+zOyy~W8o$Z<>==W)`Sea{+y#|P038B*nlLr-_K~!F|tKk z%<35$M&Vrp0#-Iss$F|x^PWnF&)8EXNRVA#<15q~KRVRI1JHlL_rA3SH4~;N>a5ZG zzh>WEa8R0hmnxqPB0A_VZtU{>(cPf|dx7E|&h>t+6r;+fM9ogn|J<*)`#r8Gqi3jQ zAuvY9tgD+woK%p`m6HgU&xU9^wSfg-Ba55{6oT`#_o;Sb z+}|7ctKE}0wR(CeRQS8V3F=^<@#r9myx!jk1x&6hdpnB{;O8bw5Q9_^vhs=s3a2mj zEe#jjovUKoEVI=*sB2LjXQ(k%QOzxa7#!77-+Q&b=#0gWp3^|RSwzS$qyj(eyt$BP z2yh)A>b!JwjD3W1_E$hl%vg$Pvyi$Q35?4^NtRPZstRVLoECV^GBBLBykgmU6?`xa z>;SP3TfBClluBV2dxqQ<6_D~#u;T70vER4=9Ib>_bFOH^q9rN2>;$8jfPXYqMeaHzoHN z>cbg-q23M{`wy%O-zvWr{bjb?NI(2G&m85Pe(8B45Xzd z&{Fds@jf|5dXNsuaLz`toL^P$1=|z4Qm1+ju+h&-UA*S;+{^j(3kKhD6Fx2e{^wp; z+3l}Tx|>_SW2t4)Sr5BV&k44H8g54cI7tb+kbo}fkaA{_G^C^8=Iv);7`nEZP*7lr zcRmoNQ?x+cWU271YT!|{KRdgp($F$eoeCCpGrN5=!3+#RwZwSdn+-Xdv|Fqp>5oc1 zvXv6MJmMigwmNpl6VuP1ZsorBPs!2t%3?b9m+TJqD}xWAI9cNKS+*RJ>1C9g?F!Q4 z`AG_EUVGHI?g>QW7L4-U??8i_?+Hq8IRa-IA#>wzE5)1DI!=O@<;T~hSwf|G;O>tA zs_VUKi1Z_6O%_FTf_AVe5fKZJV*)K+k4mQVeQ-?TwZT|N&JKSbaY|CURHzVrm+D`=v+MPwCi%#E z9#wkJaQmX<3%lXyYjf<4;mCaSnN{?;Q|g4^dge>>Vkwp$Tglz+kORY`&}bUJALl%D zI`7==Z1ZczX4l{QMF=YnxUZ0Lv~QylbURsci!2x783<*WyQSGaes>~@<5{1|$z)jK zLN_>}KVE+^-a~DN)|;O~^9J1ThfRS&fgXh9j4ji`LvBlmOW@6euAiaQ&k*FhTG%Xc0s+du)%{wZb?XrQ1pq{z#QO7+I(#}WmKK_5m4pe3oGl+INs$1cR(>na zHkB=-(Ng)9c{VHPs-EX#rt?}FVO`vr?fmj~6sqa_!P~IO*8021W>M#zG*O%*hs0#0 zd!=PgoeU&@+B^nZ{F_z}r;zO{uiYt$Hkk1vtW%co>0&RM zJwYIv%U_|iK&GW&$4>8`CiZE+9sgnRi)wWlvWwVHE?ikH=ZRabytDje|%|WYWMXtPW<4XOUyDCVjBum`99y*3&c_c3dUis zW-Bf-Y0vbSz*2@J8P`P0%Jo^0FSXA;dl#Ipi1}np

?xrL?G*rcy^Lq=9j(1>DZs za*kd-Wtz-Wm$i+ZWa8#%EFAs}(fgxCbsBAM`I&=DCJuiA^)yURkkwPXqdJHpGr}WX#vZ zs?oZ4FV^(Y7JXs{lhh5CZ7Tk3dOjE%ZbY>1)J&;|29Jgbs|Ow~328Y_c7;?(KA#lK zO%_a%GO+td^v~pi^E zg=&(1+QqilGj>6zSp9TsO|0r(AHptN@;ek#O7OS%pIcZQGtJiZM#kFP6T ztrnD;`#o)(c(C z_la>ib1%Zh$NR$jXWoxr1%o`PbDnP*x=I@!7(ia-b28%nrR;Y%5=jhGpNrL%>5*T; z$&a&aVEnf3xq0yUWY|@D-2be|d44}d(C+I^QPn z)+Vs|ysjiQ?_l@p^chjy9>=(J7c)x1gUse*M!FvDX>So>WDZ9?Wj?yd_M)-7?)8qP z+8Ys9?CiRwb6jTnoj+=AFa@tio;1Hh)nX{|#!hG*1H;0!K{Uin%R>0&?Akl+eqRZ# zVMPNO1kTJh*?FoLvOb~JfAT*PNLSz~1bN1g9P ze@TY~KV!^WCEOyElOuNG55&Xn|JHbTdtcE6yLja zB6p@fn;0@E+`?HX`uwvD`up5X_2nf4He+2O0<5_;#cJet|dK+2cz$; z{W;v!twoy9I5_;ERB|8Opd%(qlQO-Is2ct_6;1%FqVm{TF8N12ynh{x0oDYZ6Zp3p znuOxPhnvGf#so8gk)_~DYk|`q$Z~_-9f+&^%Rm_fgfcq8b!~{hf2xHF`H`BB;BACe zYIxVkr-Z*`>CG#m+@C1Kkrb?Gh^M(KCYqHfg)d4HH9fIoBPL=Y{grB$n!^HnKI`^m zRwW>(w62T>DTW>?UgRFwfR;Wea2K7>aamEC`tuBFOZZ3guh>mnu4wz2cdw7e69xEe zn6~!O_l0?l7eC@F1!_(PT-$cBDfN&s4%-?@q;vK&K<7Regp*vf`x-Qh~;cCG29q>e_Wp=CAHM~L}v>r`K0F&T>Ytk{Lj$u!lHP?_osWeFkI(ekd zeK{i|wZp<*Qh_I3hlKHvESkSOH{vcb5^Px7>KzJflHuwa!ZDXBl_Pw7DPI&Vsyywh ztTXeDbekMWOgMXn1MQAN*o z?q$i4_a`H-#T@URZmtV1HP`zC+2|Qml#7LYDuR7N1<(5N27lV_goHk6UUiYC_B(Hl zGF5s?Ew;|b_or%X?jn^>y#s1jq$I!i>KICdyL@we&e)JEOuBmHX|J#EOq9bVrhT)N zMn-#6COaY7bP4jQ^=*$Bi{>#^2U}>G(syX4l!Q$6=5Bt6xMy;^ma2y^oR`PuI14EZ zcWV}z+-3^kEhpdM6{;ItE19MBGhZ&;YJH65>L*Ge@}2d+z|#NMI3SGA?_`Ph$?FHS>cPzQxCb`E^u*3(wMGtIM0^%ns)m$%- zieC%>mqM9TvJyr5qn%a`67-|emgEZP4m%yDNdCZ(t84(9REP0Wa>R^ z*M;KyV+&Q3em|1Ch*olWEHR2C8HwUb@+z(H+CWZDra}A{FQW_ zUUlRU#xMyb^9|}fItbDBkZQ7hVPho?p(uLaS|cg6P#<(nsC}q2T=}O4IS%W*%WG^T z9N85|RZX`#5r$DqapsfUY zcH=7*)_E+7hZ*^iC*Vhf4P;0VATJ*OI;(XXNqdgC)+Ur?;VwgE#H`_+OreTu^SYTR zi_FFnkE_vl80#1O?=)wDK(ilAy&Y$w?2kftLz_H0ky8oMTmOmm`@cPUsoJu#${4ajAigW*@m3ykyS)2oHE-(h+(PHQCp+b} z=9jMvYnHvH#CO}be7GcmI=Y>E#xpX_C_# z_LN0d*(`Ah@NEao3>KHOoP?nEFG8E%#&H>@m=UAlVRDvChWe}_ewiVRl#VL8AtL)? zjpeP*3(-Fzve?aCC2HcO zl(9*Fn#ez~~8*TZRl|$VV6l%GBsWwNT|vj0K}BmoLd%ilpd{bgj9grTuSv zRbMxGodgr!Zpdy-pU*pv_>aH{5$eFE`dc&;-9k04YfJN{vg4j!c2xv zS$1`BMyt-ozMsAe@Jn+qrd~zwGpl}FkK3yWoE0U=odB}5yGyl!^$=KP+P)@oXoFXc zhg*9R?rxjcg2yuGKn?z?%_;vQeg&{bg%Z^$s;eDHDf4N_0^|SZSwj6)KU-n~DpN^u;)rW%Xr$aJtnbUt%{ET?N z7rOSLNhR7|2*+`L$~bYv_fCv1U2C%JePScQq3yBpPc3y$1IMan3OX`Xe>`0&Rv{FW zua$ir(_Fh#Z$c9zV-$}H1tpuz1#6}0S1B??s1Vv8JW^p#EJCfI^qdx+z}E3wp>33D z!!3Brzcy$QkXVL;&Wo#(rLNAGH(EWtjXnkeJ!JGRV<{Q8Syu;+jYeEl?+`5+v!d&3t(GvU;RF;UqAM zxmfe~C>V%58#}-9Sv7(_Ip`#7ZMa0Wy&0qT{pZ9ztDn2IcYn7>Vr(!4@1h{T1rCmS z zU}xKLS`tZM9T3TIbV=>)BV75VMw1{&fE+edKr{causdXm7D<_Lyg? zTE<6}0__%FlTv--{Z*2}pwBvPPq3fO?3eb+=;fCBXj`%zllSNQ+o=!tRbT37&|3I9 z!Chv?>)s>wP+eXr{T8LzAAWnXB~b4fP%sd*e|jzcIk}dFz6-RbcT}vqCOu1~7wM-b zy2k%7kbgf@%5vF)^1gq=S{>oAe$?gCt@z_>GN0}6u%>EjrVf8EqHBE|#V^OdYGB3s>ZZyPl9YUB`TLDvmNRU+Qq&WYOnIv+CkW z^;nuM$Ty)NezVyW!Midma+(+|5w7?hCwNlVuHbB; ze>OGJpSPp~qmgSxb0ttLAXXl}JbIU#5HS#~T4TH`9`L^g=pf2M}Wpnv~ z=10w62)|A9uz8+|ubEO*bJbo0NnGr-9+G2j<9ST+^%Li9)WuS~o0FD9GDh-@jy87` z^A94)FT~0Rs2bIH&woY^ODR?A5CQ9;AX)E)Lq&dS7=O7|WN29+QOpTjO@WR-X1q6% zgReWaXi{zA(-M&0Wpxkjl-cK0d?&gjx-LtzurRE0q>GFM}#Q61chU zTl-h6T6nF}u`y;(4Oq7gh1YyYK6Zbut=&M$@4BkD`?Q%mhECy{;xNbeM%8S9K&%{| zk2?l;kLck10!VIo3Cd`=pF0!1Dz>)`V}_E5wtcA6lkWO1uO?KpLcrv!;7I}5%VW^0 z>6Tc4$o@jmMwJqOs_kYsi4d7Nj?=;#V-`2rks_P!C+cWk3sb|OHJKyosj8SQ-5<3T zAn+ICSw1G`y~mvc2P{Upr^gi~6fFMlY6I;xbHS9+@~$_4GhZ1Seew!F!-L5iUz~Jb zZ0L-pdn8rZ;cBqvmI^sGEQE)oxmu)oJty5T;dSQt(Q}cyFQctcpC~-ekr}A%K8Aot zM(>ak0OoKOnIz}6eBES64&MeQ-h%4Ck|RVHfl$0NX-HvwciMW!l56HBCs^bkjY0pr zH8Jp~B9>FuCqz0WI_7-nr*IzrZV-*$(^=AYOp3UpH@<^S50kTqjWQQck3RR> z5er~M79qT!ZExhpDMRur$njd7`*0GUle*@%hquMklR`z|xG7Mc4`h;4g#bOl^Cso% zZ9`&yFEQVCa1VohgC`yY0!<;4|I9-P#%4PI7E3oDv2@eocw_(h_4Hp6baO?L*zOte zcf7PhU&j~|_4g!k;cBN{Hf6o3(hnPSxZAbB^ILOjLvU`uQF&-l&ZQyq6MhEDUT+|9 znRZzKwX8N9V{uAdqC`Yg20m;SHr)e-t*Zs{5%Gz>`!f7CYCHm@n1bLn8HoCjonU;0 zkM#W7O$4e?t5FGlQfpkF7XJoYDb`%!CFzG>KcG2SoP`>JEnS7AVP~jm)5Hetb79qc?1RGIZE-iA&s0In9L8J4*pEn8u5P zJl#xX7K!5`>rT3s@09{ey)7Qxjw#r>?tN%QCn3MwNW3%$p0g$5sU>NgC`kc%mGjqhlAaA20KyI#+-#y<-#=kF${|6@CvKK>0lMhh@vXMrFJn!&-!5tl# z#It?n5l^C6OR(R8^c&YtRbWke73%zeoa}XwZ;sy|Y`OjC-o{LjP-dE0*(l>fQP7CGMA>oPB3wW%wn} zrXV9DBXpa`Io@BZsz_=p7zK#ANnDzXvi(Hoo6-wYv z&@yyd!XorvX{QOPFJ0KFstGCUw!%FLoN=h;cJm}(Zn*Kkp|ARHc#P!Vwn_Z^z+8-s z=_|UNc8XH)1^Z>?7w0FVxuH@U4g2hR!-(p&CQ9HQ?<2HrocY7qv1HR{YWHs?95z~c z0;D`uMBC4MKZ_r$UR%H;sq{r?@z>SQL<)Q5A3r+XIx_6iG!U!l?@pIA!J_O27j&PJ}Wlj5zbqNs-hl7Mn`p%7Eo96GCKALxg z4d$ zLMBj|uN{;B_P4CsU`l7E?Ebno@}2cjnARs-gYNCmRi}& zxG_!EboQ=YBhM4O#cMSts+V%T&-n_u|Ij04+E=p@qByZMR4nkT&MKdqwU zW!xN(LpZ-`_q$o*+iCJK{>3RljmzZ&m(^|g6`S_p>CgCV;%l?F$1)swas^tRz2!f6 zDxxYQB{<0x&Ux)QVl+NgN^1lMvV=14^Q2T~S_Svqbw6z%lEc}OcvvNkf7o8u$Fya@6q}92Szfpu94j<3S zKyeJy&voRAp0^lvAM%0`-P=hjt49~=t;?hJUJxGlm0Obe+d1ROh%(cLs7Y=uf!V|| zegtBB^n+gE!YZuD1V6AVexO?1rQ*|d` zw9uk0TNZ^qiw$)c>{be`B{Nqfw4*P3YCR zTue3O0}m%$qt6r#4CZl7?`XgQP4>S`K$;_n?#%5|3lJK^`(gdh^F054-hX3Q>RmzU zZGVf1fKB+HWvu_Jjx00(i|d{!;p(%PLg2e0H99xPmTcY&fSgQ?3VjF`kwTVk`n;3= z2G{jIK(an@ra8m#p}fQ3BmPN6bwdJCkG*l>Yc2q8FJkViSOVO~XpA%cH)wrzaa2%K z<6ijZ)nYPpg?-DSI_rG7Ix#?9I9>}+^b7b z02p-;36xcuoN70t5AthbLI8Q{(mE<2Z~Z6;DG(D?7xOe(xe zia$O5aIvM``e+t?dATxUTb5K<$SD7k_^`IFS-IA3`W_m*|KmQ7?F1X=mZ&zz_YF|PLD!4bWPOLYiHUa@a90{)wmVbf z0{FNJd=yE*TQ*#u&K78V)rv_{DOv?IXat~7V&GK_mH8@3{R!|T0|NFK=JW!)gAxGG z{o8kY;5}S^ztxrpKK13L7X~+F#UY?Bc8~x`U+j6bvL3AsCIAd7fB*wHJ0r%A?pSuV zwziG~08g#TX}c3|46SLtIa)v**=g1r&+xZ%`Ey8HnEQ*?E0^VHK?NzPpz7M%J}Qqn zI#~^$3b(#Wwu^QD8%vDpOV?|rvDbojAR@vb>SlmmilHe1w6^)_qu^elXRAVM7}+0y zLi?`I7CDp6!_9Ru6mo>QZY7Xlpj%-Q49Qdf8*~5f1c3c(eTN2V;Ed(k?7*@yx@M)* zl4Q6{9uGiP+W4D6CzA*OV!slgo2Q$-&$z+BFVA;`FizjG`Rzoh0c-2kD(C7_C{1!V zwYO3>pvrEY0>-BbpaKhD{4VojP!&5#Ja6IDhB^l)_L~FT1Tvgyg`VajY|iIs5QDup z>{Rx{XQrR7K0I6WZ}nMvY!nMXnF;`feFgZ(ghX+n)LwF+xG)T(epuq@t9ZIQ%Y=Ek zOki>b=~ea9$o53y{`~VbCb0V0=sXa7*h3F^xKQ`sZ%1cmS#2jvlVqu3kXpw@4uDnX_wmPI>Hx*61$f8^ z%&)8&w4!o>N{`Gf6~C?Z&MxyEKOXwPjen{1#swb zm?(i3K(p<29TsES-QB&E{PuhfcxI)`szSq3$cud76N!k3m;w0-fDQluLEU$sTSlzp zk6B9)ho4Ja^s4@aI5|H48^y)Q?f{C51|cPYujBXb{QSHhn7Yhwed}A<=`E7;<{li~ za@IWTXl0ce>#C*#Z8@zey8r?+zIJ`nE;}6-*=Czs_rHp{UE(xsnmPlQT~6QLEZ)wl z7HG6=f4>3vOd9;qYYfj@;($V-&Pc*P`5z4m(rjz0sSv&^Gu%Z0SJ?hEfD$h+ewekt zX(y1_5rr?K7MdHs??(VfHs%eZMwB66r($XCv0Vvu4_YRc4Cv2_& zi+zL19XQ|dzZt&WEQ2;wzAGxo{8Mb$JY)3TjU~#lZvI0C#`FcicmJVG;hRa|Ft!AU z4jda+Nrk!qclm|M5mi+>>U|C@>L^3!SbHn#$ZoM1^( za9Mz@zm>3ca7gZqB#R8|0Ze*^r;plBlaom?!4h_J^}rCffc?x%pe%4urkF~TvjRyP z0iMfU(U_~Gg6-So^j~kky-eusS!nh)N1yI$aHQl6^Yig(q04hAKi+Cg0%bfaE349Z zStgC&_T5Pt;3oAavnO#KPCdW2<5)SPZ5zj{>qdDD>r5 zpe;xM5PUvh_exxkN%SH+Bh9S&8+x2f_}1 z-x~T|n8PkNi;Ql2nVHx{WM0*TpcCz9-{Ni%!FyJvA;^RCRJeENGwmM4%`p=uQNqxl zK~)WS-)OAIq;f)($(Gr$!b@EsO~h`YNf!c1<}i4bq<~d>c6^Mn^3A3z%|W0_&jaLN zEjJG-S^I1;rT(qsFCt7i0@7d-fYR0nG_n{r9`WM&^Dn2y(&W*An%kZjeplZi?G%ZsBc^fm6TI(cP34Yh5TCW%|Ees}yV-yGn&@5Dn8}?b_ zHJJ@vXv0L6XdAdE%{jH>9qu~%>u+sst(?v}rjYYm^t{zJU;u#x=iL&Zo=d@h*SXon zn-3Sj<5+>O>LViX*=o&UMU1af3*cGzD+|uQ6kPDkvzw`w-)lNjxd3V(ORYW7&B|)J zy+);AS{zJRL0=+^%X*eag#GLcP7=2>P%8U2ix3<@TZ~@WHoE<;_39ZW>Vgp{IMnJI z`vbhgJ$W(WuN-0h`ewj$4}m|(X=|sj8GP4*K*RynydMLVTU%Mh*0r3JXt0s40*z}z zON%(>0|=`Z6;ZBZG<0#G5cUBbB4gOi#ri7ZW)l(hn?@Fi$rr&icthf7JB%cM1@!wP zn-2R}dHip#Om%EmA!Y#Aj(O9bp)65`Bn7GyvUwn6K&J(0IQua%Ai51M1y_G?Bw|yH z{B(za3Q0s1-f7}8YhTw}BynvGbg3$Be!tq>+KSgUgh`jS-gpU3V9r(Pb{|mjSTGm; z5fG)3idaABkiU%#3F}E|y)tk36Zm)qIMa<#APmC=_{c#jH^3RnF4n1#ENwbez`QHa zE(0CJvTr<}-hO-63miRr1F8jWc5%4+cW8+CLAa_`ioaIkWIM*N2Rf5AVBlw4>2u)% zB&&#Hu>58ppj9l{bH%h_Kw12o%*S+f-j(RRHPFyfmuUxjFPPvKWo2cTrC_qYf)vA7 zn0y-GW~rOrudJoT5SW--?8ihf6lJgSG$N`2)TlK=qle2pCnqi%I$ET|dHf>iQP1=NEei1sB;c>j=B9u7QLQy}kNn{EOov33g1XkU`^z zURjCD5mO!0RmdtP*$7A`!c@50+S)u0es3TvLK{7f;qEux^f0eHwT=m?X}v|arVRV; zxmE)0K?7i^7gSa8?t5aAiF|I35Gkys^^(~>hrQ{D$%ClXs)x#7aRuj`f|`IwRyxdo z?=6jRAqJ9i%)6q<4}t#B@AK{dy>Oxr;xwvQWYekLa`+6>1$vpL)Cb7XD?smH)V(PQ zcR85MFc#>6yd4rdgOWdg9?J=IjXE41Ew_%N0Kokl2%eE}Qn~X7vCmS z+OY=*$g=1yO?DwZNGkJ@#xx3Xa*%h$I&?r!CShV?0{FkbUxJC{RhGto-I5fn{ll=S r|A}`0H_Pi^x7_^efa|~A!T_TrJ!FM%&2y6O0RQBrRUoC3?*soACs-|{ literal 0 HcmV?d00001 diff --git a/labworks/LW3/images/7.png b/labworks/LW3/images/7.png new file mode 100644 index 0000000000000000000000000000000000000000..8a8b00e715840644207427d140df62202412d7fd GIT binary patch literal 11366 zcmb7K2{fBqyN;?(XnR_vis~tfwuaU$hK>|PYb;W#YK)j-43VBrPAN(UHMfQkLsUr& z5js*e6(PjffmBG+(ntx(-FpA~pa0x@&wuZ+R+hE+@_pal``yp`4Ey#u8*}k3d$vFz z5OIq$r|cjQp~v8pyJ-XXi$h<@LGa5k{Pcxz`(U5&D9UNMLYyp#SB4k=|iQ z|KK1k^&^_%+)_{I7+vlr<%k`$FchlLqT zOvvMh&5oG{pZRh3Yg}iJbo#<{ZVxxEhubvYWk5%tIKF-TI>@A~)jSyjd4BUYWE~{> zI7A52wC^ee;=cVD1fsENALOdk`t6YCqU$z6CQm1_MdD!l)80QhnQ%WhxAL6I=U4*> zq;TIR%HSZjug^|NDVJ|VZxVfcGGQyOscDpZ6aw*`nS62m;GsiMCg-H&v2y3C!NOFN zGA#B$SC)>|gn-Z0@$JsBUBwI!52u^JqHSza`g<6&RyhN%rqxjeJq@}#I>Qv+rB!!2 zO~8HKj~&Muvq+II)I2mfdHUQP_GphpZ^01%pzLl&r7y)I=Qm+rMad*wK|z7w+e-K? z#jEkl{rLe??;fD$+m#(%TySmj7+8{&h7%f1-Xbb$`b`l3eP7zWds-ibRiKAD8g$iU zk8rjoj7A}xuslOW19nF0_G8a)&h)1={2KGi%cvIK#j$uEbNQWfbAf+9cBWl9-@(l6 zR{ZxudGR-?!Vs~O*Y_S98yhPtFYkYOQ&d1tP*n2&@bV_DF=Ez&^DP=yeIf9<2t;#U z90idxMmeC-=z|9j?)kb}P_SP|M<>_8!`{BoPn(AMAhHP(;`xwgX9Qb=kLF9?bFlbjhB5|X=EC^d;Goh_lQR*!S`wm5|3V;Nyd(U+Je=mK7<8j2cFZV zf2Plyw12^|ssazUMBl6c+_f85{|n#QJ+e+*yEjT-?tsQ z^h#hue;YZ1cn0T&+N16KZy}l9`EFMj=;53med@GSiY_PRN`2~5wN0(%qqc6bvC+&Y za|o~8Es@O?GQNpgf7&bm{+0f@rQZDhNF+mo9f=?Nmd{$CD$dXad@njJx@mwyQr2O? zVoM3HC?rlj&-FlYQ5LG_pqy`6uu1syhRB7Ud_B&%Jr|2)zE-tAOIEhdXTYG5AJ^Nn z=SGd}$q3f)l9oc3p~5yP$?m_{(0}=oX0KK9TFK(w1P#-MK?w9(M9JIKr+VGK^DKFL)=u@K1GcK|k$8lStTu<0NPtrLo+IqDh}@!H&1Lv$!MY-bTvzbkJ95wsTmBAiCR}w9)?$Fh2RnXcQR3RQLWjK1NZP9VdGG;c|# zb!e0y<=EJCYYw=r|Bd%e!D91C^xF`mfEzGsb+R4X{p44-IyaA>Q!a*rpy|+w^C}X1 zLNbqfzq=&Z4SBAqr-->m`kZd{ol#!J@7ZP{{R?IW;6}l(7Ps!-m)IpGwe2(<@_f?~ z#U3H%7|FS~xOk6gd{a=vl%$+~$Yd?y&luw9@O0LfNnnJx- z%N)xoG#U+K5dD5JtrK$fga2C(xx3lfjldED}%qAR5s34j^W-yzF1YBQEbb0zawq-AC>rd%WLgQ%sA&0t3J_u?1)^N_2a zf$s(DxqKdb*2-f!Jw*z(>ex4s%+k96rd133BkOK+>r;abhC(_i(7q`XSO57R``y@&sSS~5 zgNV2&^Ow3|r3-$ANM>)Veaj?0{3CfYofgzFwATU?FZf<{b+vx_I!2eHepvPsEIU6q zc188@Gjg)xA!TZV?)@v!_)%_(#Irk0gKc10D?M7`pSrDsnCuIH~9{W0dWkFi1}JD1r>N#hb+*OhOJFJo+g(afq=%fyanbnl_V-14OKIPu&I*|=t72_&8z-uebKd)3Nr!i)r@kdPaC@XKL3t@iAQr(Am^TW(83YEW8H^LQk8+=94zPu3cV@47u? zM$vBJ5^?-((12XHt*q%~hH>PmHrT<_PFbjuEA`3HdqvMR6Wb!r?C|}cZ0C=0{1qum zT8NZ{rJt}2%h@0mmS?1>8kp@(_?+jK12<33zr-Lj+gif$=obD{TvXkY_|6-b?b*0~ z%d?#7yF8<(i}yca$7gz<#VT91wYko>9LN35n3N0G5?>Hi@(-Ab zqr1LR(HBXH$PxOR1^Scub&t4&NaFC<6BKV!d>OfWBl0W5ySkjSQ5n|Z`7el1rd{mW z(|TjRF9>r+evDklOWD+ix(7bOMjj!CGSi=#k$T|Jy-*)U?vAc-ytQ~>&8tQ?)L9PB zf~6&f)Ef0AS=jle^6oT6cj{JEmXp_bSK$Z+I-ohCVO;l;0yP*|BrV+@ROlx7|Av@| zifWjcu3DX!!j4OIRfOZa-bLn@hcDU~dHVVhP}&H&6U(ELd3(#&5fJ zj5~p8v9z?jpO=TfDJm7f9w%QXxC3bQ-1>NNF>;N70zPUo#Yr`q|2;4I<7VTf&-ZA} zXwp$FEkg9S%MlR``H8|1Gm{16F{=#qfxcoZ+n9^n*P~XxwQ(wg(N-M~)$S=8uYT_b z46bjX$FwRtsBvb_NffgC$OewVV}Qkg(XElc)rlmt!m^4A%3x&)e>*nX2!G+Q?&Lbi z?xhVnSF^IR6fI7l7B-c8T3T8vXiP1~;m&LCVYb}Q$k;ZW4uQ~B*;Uuv2mudV-Q0K@ z8@JKicZflD=Yg*#CYi>0SRs)MSJ`@cdRz}~C;(>z0|Q}o$knvqbHaY3^`QsV)d#WG z*~=|bNpEV=yhuO*#ivu(LBx>L&M$KHLr(xypA|Gdd2$>Y#d2_W&jW)AXOp>%eEv+n zwtt@@;CeO_{KYy)SJ$%Hs+M?7syJl#bf-|QSKHQ$$S$2#k1AM$U3%^1H(M$%lAJsQ z%hZAKaXge&e^O0Nt&veyUK{$!474%v@iJ5O&nDPYzm8aVsGQNKE*=O}&^^$V%YgBm zsUDsTa%Ih6gRYWK{i>pl4k=YGttiio>#R$ZOU^=hte)m-%|5)stu{`l4EIjMvJZ@? zA#@Ty1q5i-BtPfPPI zV>3cAakFQJT7N4(H5#j2;+u_%iik9%`uLFKv+=QGvd0$aJ7+l9!*lN&r2DhZYxfYW%o8jvQhGXKfjnB$Y0+<@HAdkjPXtBb z5g6*CYVGNUV(fBl_X#>JW!u(F6uWGdfMgE6YsZd1In3o*Hj&>@pgU}J27F8EdwwuP zhkeF5ijBGOSM5ZX5b1Xjc=4No?V)VljmnTs}-k@=p=7P#TU(InxKPSRY{Q97+5 zUoe3k?=AHVdhC5G*GuhhL!N?{gzcr>*`9kw6#O^2arX>fGu+YK*hL|AeBI|@XBWsAlZLWj zBfaA@u#v%OqK1L+|D{|1SdTxD{LUShkdy72lU@2-Y_P|Xs>F$1c)rI%E}Tmy1ChXH zM`knHPMI4}Z)qL1CKslK(P^*b%+Hcjqgtb>iTm0k*GF)PP-?5;W$bun<}ELKySq8F;Dr$*+;8=~)ySUgs%%utDk>L= zaO+%MWX&Z)2Y#a2U&@&OrNO>X$+PvA-ga4LB5g-lmF-*IW(8$a28=W}C}T~=L{reG zk`tNDXjZ}L#_3fRYA$>f4Q6F+CT5IEbaHH@p9qMSvv4qI8}Z1N1LgWl~t0Z zl@-CScmL`qQ-0z8U$`z7QdV}tKNT;>iw}B%0OanNhG|E1F9FRt++Q()AFMX7rZeiz9HF8$d;@y$%r%8tf z8i?P{B;cZ4orpLS<2S3{m^~Z$R~T|OQKknDwhm3tOcgblAB#%h$v%HfYQuH^7sB!{ zMK4WdRH_Le*)TIEsKOZCyI;F;&-A!}Qha<4qmt#XLnNrP1Jw@l%)I!~Zq_U6SZ| zd^Cl*xq*)HbuPh0jIkpDGTPZ$lUr5>c43!anQw(siW02k0gRf9k4t%Hp~cy{ zJQ`bK7C16IM*Rqr=?=|L9->Y;wMqY%Px-&${ZCT+XU{;SFxqI#wdW1GQ0NFHwzVR& zo6weuzQh>Y1J@bw(BTKrX`e%eD6vaw7$%Gqj3MK=)e689dEzkA$U~8=IUm%y=9gcs&@hH(#mtxf1}&&w<5tM-03DDd@DGQkO+6r zJY1CX%TS+`qTVGI`JUkzYvLzS*AzJiR6D-@;}&mU-}0wV&rv-vWX9}9zSHo)Krw?6 zFh!>yI&{dYBSXU(S;N#j3VHt4cgtfSwH=+E;Uh!@YU+VArN6)Mbdn^FOeVKXH}hEi zK)jdw=A)f}i)a}BVNbGv!-=9+8S6te&PM6)7y0C}vkQr<*5H-r1(o_$0_1Y>5V7r350 zIQDF2L1N+-#8@NezVXLz^_Q!Mu8IPvhJJ!rD(-0Hj>krT7Y$hcK9gPq%;1}^KHM`A zt1K-&V{L6+GH3q}4^&k{!?a&X2y!b;YwKe$c;-0SZI)VPS}sxn@VBzEay8@n#%+0y zrjX}fL(JI1jlgc;^jT^617;39=UG8~XlQjKi8RpHcXaY_X+wj{n>TMt=62maC2{*y z_Z4YiLv)63kXZj4tC<&s7F91tpt=fCME`SfL>$nXkl5| zL3g2zkloKEj)4}Jrr4Elih0h>M=?~#KqpKuYTFxo*22PK4fnxhNou%P$gfOpy#DM0 zSYFR9`!a^T{r&wxVwXYtg|2$$4%w4cXkt!H@coB+Y65bKFhnoGqF@8O&mz4_(jjYk{^$uQh2X7bH^Ku zfyOo_vqpx;<6lzTZjHF5&p)%zh1=gloh8?ZlVeecU@wcU=DF~at}Jl-kEarfFanC< z-?l$;dfSd%x^g=uOup?`i;SL3FP_k?w3FtkvO0wEA1{--3B_LTOvqm};udMMIqk({3i3&tBiKEhY+?uo?9*&DV}pbEgcCz42G6t~|H61D|x zWQ?V2BQ7d9o%eeIYrGy872mGZP1t#$L7rQEA=_T=Z?oT@^vmZ(^10*N^{Lp?eP_uE zX}{x|tEze$B5B&(VTbhlk~ebU^62ls*t55}rs`8|$XA+hQ2|(E5p$qXV~BGlRtAP zP0_9N2YGq*xcG_uMSbdCxIefl#~GC7M06o&-h=U@4j4t9;RYh~>8ks1R)`1h!?wWL zZmXz#xr{RmT@H)s59E=rQjfWeIP4*{lo z#+M^|4nCV;yKZ`FO8f`kHhzBRE(r-gfR?Vn1~4?V5eT{biw&Int$cFF?HepI*ZpG5 z)PpP&G)lk?ZeH?9mV-J0;Y}mJGn&682bVTCyY~P%Qsq%7lrJwf${Y22Lm;F5{*}<8cQtsy>BZ)svl3qWDnVFfj zml>>dE9t@T7vA;sQ1KT@;S*@C|9Ddjpy|_h10jGU9~D{S#ER%2KK(7~+yi3oa#z|xA6=5yiq(oxoA5_HtJjT0GniIJPm;D3Fvqg|KN ztsxCB(@=@5YKf*j0PbLN{uE5c(ngQ7RgAvx;pV$|!r%5kH4`_URF`-r_U&o)9aej% zr4~nhuhzQ;-Sl2xhB3e3#E9#bQS*u$$t_Nct!}w+!S^t)tvf)MHam2>Z;b7nPNCA{S1zRL*mJgbe*7Q?67~PKihmWn|8d!i!}?;# zTSAUNvm+EMk$`I-o?}oGlD~+~ES*E9pk&v6()VFT_xss38`2k;aP40$;h26h*Z;iRE zew1qY($ZXBZZ$A40Ct?Slheb88XoxR>FMJh+K@{>v_#IixMc2)|KSNP@NY|zYh0wk z34y~$$(%vA^ddmYY&DvH6y%{7T?PgR8Q}atP^mK_;k$R znvg||=stMxU?#zI<;mJUhgXrE(%1H|KZAm!5fRzbKrBa>12m2GU6DQK;gLUBMn3#qb1%P#_23HT*=2hfE zqXK|&3VaRHn(@gTuA$$NdKxfrkU%6ZdTiZm6x|9=RlG`ALLd7OaslZ4`-)w8#%?Ww zRW^srM%(I*M;HDNV#<{INlfPsZG?!yeOFB$pW6QfSQ!68MO*Ly!Z&V}J?H2+Fw6&O z;wCRc;kBOdQ2k;V;M;)U`vX==Yl^9Hk6-cz3DX!zv|Ss*is$F&*OoJu)nE?hscGF- zNXQO*h@45>1rPpw#=y`}sh@UPrj{>bD#K%tZo)ON=<`Z7#ugPRs(CcSK(hg7CI+{~ zf4%;zi~gluyUib8xpKvj>K^G*jEgFuF196{%8x}{8hwA)Gv4ZLvZOX3yZ!PVAHz?%XAE-PY<0hq2&+gM&^}pFiub%6A;NuvIrl5Xg0ZRajqi zjHT75IO2HW4NR8@-#7b~(Z{6E z+1aJPd-u*J77c>p-^Z8aJ)!0)qMkBJL}Zb{2y>-KD?jz?{`LO|x|2M29s|DpHlwds z_ow~NE*4WIB0tw}C!W6yHP1pe;MpxZN&)R<{-rm*HpLNq7>=@WI1}2PL-5EYb7jL(tpT zHwySXM?1TM@884KVD;x>xhzi2P|a8Wk(k-ay1d%pjKeM;eXD&-fkWmD3%v>E!|}p} zQji3=b2uE~fX2qgwO+ll66fvh?Y}fX6%Z7(So=}y)3aRQq?`I<#sOQ(bBgm>i>E<> zEw&8TmX%qy{CK0WTxIIa3%juXy)9d^h4< zEclP8TCCZOPlNMgrZbWCFKe9L+{%HPM2rxvtD5E$Q7BX`aLa)G$fb@(O`uWV-biug zYI@3mKbWvpu1{QVbTV`xQXSl{jLTa?@w@lSThx%V_Gp%TBG-M7{pQO6S zRz6g7!`6+XtojT_GhS$Fg0oGJ!2}6ro12>-*Vby6;&9*U%U*Dv3vXLrd;fqlLG4PQ~Ooa)wk|NfA8h93AMHB)6OVHPiOiXRfL4Z#eo{z6q@S9W{ImrUJ;|n~&AIYR?Y8j+;2e{6zRAUMr%F3>^MuqX@x0Q_4wKW z2pT!I4pb^yBltbY;4J!7xwGcfWC>6Qyi7Grjn zGm7kqfmM!W2RGwD(*#2X4b4cO!`!Jv>O`IpAT}3MRCCyB)l}i(6CV%Jae5 zi$*4K#0W3uJB!T@VhFf*q_woc0S)U%n#Z&Cf(NgOh#KMNIvs%Lz-5iS;v2lPMK&^< z{)(pKGh$l*(WJnEEJstpQV#(%DbRcK`gL-+m}`erRL+Hk&0ADG_X`Sg0v-vNNb=|? z>|)%vH^9Bl2N-lab#d$_(L>39<;S;!Dk{4l@)lVn_MnvpxyWOc;Vf*TTU=j%0UUG- z@b{NKXA0xeXNU_90DhGGhnQ)b6W(}hfWK19GY$h`yB zTL5^(X^ahDj2hc@s<8Lc!gSYhFE1}aabaO$%XBxCEe6usYXErEKtY-VR$AiPvr`_KFL@3%L7eJT3l$G1<{V-}`k+#9;|T9&#VgNC;@v`8jxR~#6g z*oi0SzIJ%%oQ_d~Rj{9bcIudssy0-7f*W#hI0QovNl(}!m?e(IPhc|%@ zv#P!<7S|UU86LhqNm6Z#S?XRnUwsaj zi0UmfoLlzXk%Q`PN_h3+OK;(I5mCwS3AWpFNa*&qBM?ZFK06=ehMf`%qtkQS=6K&T=@ zr1uU1MTi7QLBr&e`Wz|1q}=wb@ztSRfDxyUtBb z6A0wMYw(--%MtKDX2XRN;2))c8&(0P-Yx;bcl?|o26qB{JiP-v-5q}qa`y9g_x8Gc zLFVEGdCA}10s?&em87NN|M`jw-hQsq`jx_F;9ZXT+_d(GKsfI(eh(C>7rH|r7vps_ zubG8ptj{5QY{{Yf8v{fS>4s7ZO1jjkQ%?jg1o83kvmX_m>AUdF-#rs}rlx`Q79&1fn)%!!cr?IzO?L;y};Yces?AC?YFzikkyN zd-zsGFxY;=Eoc&Bf$Ziwil44}wJx3JkC#)NSoX6vC51>X*(zTQA0BPI#V0eCl47Ya zq4mbtl=SHig=Q^2xovcX+qayZhot~_+;=8ue4?H-P(V;J_3pu`T)L|qg`1B0h>^3E zNDY%8w`}CmhBwDni6-9AeT0n(=^dRhu~U$_O^9&(*sNxYj}+vIy|KQxE`${vFmg3H zG8iAV=Tv6bXc4dS{Yml#yW+<}kyhs|N^cn%#iymI{kTS%Q*V5zaR+~3>sm?(sYI4; zJus~7Sd^4kb&0}UZ_?Ggorxnhq9q+y1r&%W`*yL2D7`X~8)t~HqX(V5+aXU6qnQ;} zBLrpF2I_sEK(z{;1(4iFPd%zfRc~0GtInjH-h@=~FQTb~Rq`60i^aX)C*9YiRy4A; zQWJSjhf`R-zKN5({XGaoh#fc2T;nyT#LmX{Y>tCpVF957x#xfTy~7`agM+VcisZJmwD>xZ zR##2+^m?d-#f|#Uk1Q*}+dn$mdhlt7qfOP_7_{fqrR`c1RGt(RUG(OSQ*IPL_PtlRZ0tw7zCo$aQ)h^lQ>`5t|QFMNxJ!Fmd1;F1w(hMhB2)hs<$P$WBY5_ z$>`wM6XT5)$_^h>!?4|IKLkGRPgE{O2-$B%-Q9FIjR?JgLE+A14=7K#Xw6dcMMT*K z47AEBAKr&c!KH|;O?}1L&IHxF3Y`=|B~OCtrO#Ol#(cb&$Z8d1w7sKPPi66oEhv@j zz>0xoPil+A8r@>_?uTu$FRIM*e&qts>RX*LRuU-Jc^U9M7B%c{#T>^uFfl`ZxH&=& zK$>p)aStwLvwAf#rpN z&+~_$xzotmvk0EaoTl}W7uD_BnJ|qz&^-eMLW`Hq)1*eMPlqGgAJZVYY@2>Xt;PJL zW0lrZB0i$%>-Iw5@n0eDSdaYEL+rV9CQHi{6OlDJA&pN+e+O)`QehSA=Puox=RduE}$FG^vx{gs6-%8$9UhFW0hno6d9L4w|OnPRH`8F%!*(~LIQ$6QKX~C zliBfwf${_gnJ7apf6^dye*GNuS#Rh%(N~ejE~EuT$>*_KustQSY(QJCRewdu-r14E zPrpncZrCHuj8`KgIpU|o3bkifSrsWaUpscKhcB@F0$E@>^iK~RiG9(h`1vg+W$Meg zxihJcp6A?p`GjhB7nPKE{{SVtqPttyl%y}VY6~^?TFopimKoz=A@Z7xOV$_bQku{K zYEA^zG~R%6sgKE*EqSZw@CHf5(6DUGmWnBwa7&223P$fp&Ib6vgGr>L+GPK0W_jKyWn1r)8^s1tCOuKT%`SYSBW$CCXP@#o(O{}|>i|S0HL>fKg+)Pfa&ng& zJLJ`Au_eXV^0*KUI2@j)9@WzFqeI$bpH3?*>vO5*-KLjVlVtu{6^B^~bjWS2*nGFAbx%*qrsgK# zk-;cBKB~C2)j@ry%gE5W^>5I6aY*kVME_a>op3KLjW1%&NoXWXwUC~%8=_JkGD}nC zfZR*HGd$0HMMb5w89^zotqrV-;)dMjOZ|3WYe_oFdTwqmY_m_E+~Ytu$)?WYxnnf9 zb_Sv%bAP@n{hNB5fJ(@%?EO7_;NA~kSvfhvNH)C&?LA-KsRjK5yD<3V{pq^N469z% zmiz+rbWI%BStErBu@aL4T+X`)x{z|v@ThWXz<#xhhQ>owaOLgTnl9(LRlT@lf~4Xy z-}oBTlVts7|2q_`gb>WSnrG2l+SJbFY}++kDo?hZBOy}?gOy7GdTSUOSZHdoUiSd~^?`U)mCNFH)ADpkx zW`#KBLJvY*ey>`9K382XJ+}i{J zBtp=t@^;V7Sk2jBc;K+AkpYrr$26*bVMU~5j+&B$aW&O3k>v9)XP1DtdfzCSMVvhk zxAuWMFBR;v&diQ{*}N}hDkbFCI>5DrW@|L*q=mke28FeHy@2}To!i?DR4VsVF3oSaIrcB@ZD8(B0b4Rl=w)MYyFqM0H_O}=%?G5f& z;xUC!xp0BNK=%IH)KaNs*SiYf$&{GN4f!5Qd4+V8aV6L#6kh`H^Qb=l(#&bzqo*Pt zOH4UN784TsYmYkpF}U_L5rzBhUIMEp<&F#?QfOIVpiAZvmzVf@q}ojrqk+@-X?cgJ z_R&T&d#7S)y+*9i^Dpq1cGx4#nJ~Razg*CfaG8a*CvRe91fT!&rTkp7sT}KtysM`% zOW6;hdgZ`*aM5#?V?+O9T2nMlM|^ zJ&cEyh_N}g_{p9xa9|`hsgb0o!-9unb=B}$mrs67mbK`{RH(vY+08_J)a5CyD_QGe zI*mci%eK_*nTP_M)aG2gwT{HL0MMCF(O0`~PSVt#@m6!|$xyIK;kXxpynf0B^#>0^ zLfRnz^dRG0z3_d<_@RbZs0$_oL9`Zsk~;oUFlgXV&oVspHWDFbmdYRiRPOr-W&cp9 zocZauG@Qx&nC;HQHsk3lW6qZ9h`A7+$MN|#;m({FMj0d#jp%;RH; zc#WK|+pl_mviK$>Y-cGYaJ_b-xU9?|=hjUlRq|*(iTT=V1gY7wtgK8zT6zNLN^<8Z zZ~f7*1CYyqghKL1+@IJK7ytThHAtnP0J{Fk`B&U{NxFIEIq;k~!IN!{J;Y@yh1gxHRajV*cs z4EDaxJlGVvIXXO?3k2=62)K{Wt%|1aPnDFE#J+1EfD|ZhmMlDa{J7S2AgeNp1U_wJ z(7K78UFLFc>YGMV3v_?WXg`lty6M*Da^Hx2%LaRGZSBhLYDMYAj?(f|aLrRu0UZKhD{*B3L-YolkJ!x>Oh}s~!^6nbtX8QdE;*b>5>{xK?!2E2~ z;3&dPVcquB)5$aSVN^p}E^36g7o&dbZWVgd)j}`be?4YVqX1X=ic0%UqCv>=Q|`>p zZNaOSc7aLJ3tOBuU_)`Le7h$YvTy(fgS^vzLa}T+08vXjc@+YY{#OsZ#wz&kQnb>I zGhUk;lg5<2H`mo*HrjTk4|3`N40HPq#HY>S_CDR%*A`oh%oh2KZhtN3-eXp+`DIB9 zPCc9CH((Zv1)zMVz2Q8UuPN!}rwkNbbCMRRL#mA^7>9aeT;Jx8pq-i;x^FqS^u)4h z&u$*mi^CvENdNsEP|=?iLhQ>D&WyS#clIQV_19v<;6qAhjkePXmqjT>*#t8Tit_E-TYot2B(nuH-LJe>^Oq%7 zuOZEUu8IE=#@0UONzPBT=BmcJUB(nC&;OXa^b}_r}h0xA<*1vu4W={=327LK&4@FEZ6@^6HeFjyH29T%D z>X6AqJk&g&Dw8E$?|j6M>His!{I~eTv0G~+&m`%oqE^e@->mU1T?EB~KyEf;>GpQ? zkGO6Lid$^R?5Iuh+xT&`m?_EaW6T`%a8ogF67aZEVY{wwZjt_91H{ESmJ~cZMeO>{6fA7suGGoP&K8GLM}2H z{Gi_RYFH_#+;7<$)~j_JI+Gbi-DvZnx|Pu8z9{Y;@We=@A6vN z5cItr4>z~LELDWz4h_g=0)gNw4|&%szjEm7LfZqS$h~?SDD*6qfzrn|vl%Fjwd-5^ zFNg*w1nko&Ffw7x!`*!d*Nh-1RfON*vGuucQEDZV!^#ZN_g+3wv>9iT4mN*VD)XSZr5*V`XU2f~ep9U| zWI_0eq{2T?pFbrV7d`YUmng7RR;e@Je>+OaDD7qeRvlhEj6s{NXEBTF@Xgbz(Vau`puN=nx)zf_R!m*8fsZ0?D2OqVAZ@DUsLm(w0ARM?PKUgUFXxLp(Fg1 zD?7$cUbnBjcSDJRMi7-VFCJ9{dS4Us43b~J>3>~1<@`uix*f2X082?h|jpsNmQ8zU6)RO$Mh^G1-?iH}3j-t^R+Q`tz|JW+(i6qDzX4{fOy(@oD2SNFm?y z=bfIR@Ru(T7wpP!_oSYGI9I)3n8AOMZ1`c$zd{66ECoQScM4sdTil63mwJ92ZImQt z$(}e&Oudi161>fC8d2U$3+^axa4{u4cpR@dF@Ey!*x%0GoJC)#a zRPg=_L}ZT0@ukQX0Y$&jQH0OC2xZ|%;W|2eyuMK?DlQ-GdY4!Y1OGYgFrt`;SG$!9 zLfG&ia=H7gSOGUrvOOhL*O8cb<8yy4rW941>%7!o8>9Ig6^t-#MyZ_u(k5zu_f!E6 zLH}0Z4}X7Bm`hIc{Eco#A~-f$kJZ*O>6Dq)M0y~{(728!|Mf0;&h#+OQ=k2&)1dmz z+RSspaFf921-PC4oj0h+Z$IApuirauqm8`8OR3Lz;Ti9pk3?*ZExe{SY(C6275FI< z^bZvQU7BJSl#1-iOG`@&pphp^3JYCr4a5?RU0n+atE=Yb=J{hKmL(Mx-q(3RTtNrt zG&VvrGc%`KA{y;OJ~4qD%+9}0R=04(NtQC}ADBINCDi4(D?f&v#?IMDb&s2fcc{+BwBEMTZ}VON!V zO3KRQX;{Td%-Jl35~fmUo#CNFhn(s_>5yTr4tclbqeVK@u-UInUaKA;fTm%5ZK@jE zf&wl?-d=}E{%;aBC1k5lVDBBn~)8UYQ7)4*z;$+@JI zl=DftE6Gr=q3K$fxusnXAeQFxDNutJl7LN`=K}UI%V!0?_h6h%wU4 ze5y$Ey;LJ?o?e$pwGab#@nJ54_U3Ye zkVW!L7U!C3IPi_dv&pUF)5}>Xi+K#pOdP`~YMPJ1?U5t}!yXE2IazGU5zPxDoe z`WSr(qVN8%W)?qR=ep&~hJXL`69nS^&?h4iw2wuI zrl%rIe#!$PC={lDl)8>n)2LnFJI6$9Rp(*Dz7|>XLl@;;?}}I#7On+tQW6n69+Q9$ zw6wrr4UW$Wv6u&xF8%wNsdCVlJV%*2$?`NCN_cU|d)0Y8Ioq8N-#yc#!#t_r4HR+{uC z*qJY7VJ}?_=p9u);lDq3=2+Pka(^60IzcbL)F1vk)Xc=`4T5ciE)S>N5li-m%-IZEOO2JhnkfI?HE( z59aAN5R{Pj@=l$;u#Q9tN}hZ{I=Gd(dg(s6U29p)a#v1XCUZRWOtk}v`1Ili@LUai z6dX1lgGcF@$oN!9CwlI{c0BvdvITwBJDDGk6ySI@F3hb>q35m7OU!PzOR(eHm7C}M zdnF{`*dHA{QN3mkCxWAFSJb^`)MabW;iv0Q&#Y(SWczDTi3s?GlnK4o-Sx-gKNtA^ z%Dsk$hJY#Olyj;23=KZv5Y-$O7S=gt8#rbTI^0FCy7@@z9~bx_7ipagBqZdMS8REqL!?z ztUJCxv*CO9d2EZlv2hMa&tt4lgCs|(1b+|khloyK;G#PBnzs7xOFllnfG*J#x4DKu zK3-l$c)X`vNn2anPckYC)ixMT2XC=x4NLEncrMDs&fd zgKJz;L1W_u0+%TQ$~^qq=c53gUUOd}XQ|H6j2Z*U)%wl*t^=$6wahrQfaOY!REpQ_ z+aP>3^(TzFI55Io|5{M(yryTB8xpXD@;0z|*?>6Y)jqmj2vw~(Y z(kXTW#nIlbTfPw4yZqFPiu~u!!gVk7YJ!x*&63iE6ZjXrf$=rQd9yWfKA^%k^@-Pe znHRmd4RU#x8S{=@M3W)ur7);0kf*6PO`OdE=ZTHE5mZaYR3%X5L(LXQ2@_&#Hv4ma zd9qsA=yq4D@Ec<4xrgsgxSAOg1(Oo{zUVi#El5T#WDLgytIl(E&eg!#R=aHH99o8=_)Pn>*3Zu& z0pBdzLKAdT!?NWm*G*}K$@Uqoev0(mj-Yw(&CL~T!5oI+h z#d9@LVnv<~y%A(J6rhIysuUC&Y*DnEz5mtaUb~)N|{wFh5#G=E_it@@#Rc zXl-Pipz^XU^jSTYOUI<;YfI*k=KE1inxP zq4kIn%=YAvy(x))fHIl-V#9L%5*C{k%;Xo9aT2uRwLpzKmE5WlSZr@68ashBAOq$f zTKDgG!@mroWc^L+)HB9)OF*bAQ_4_fGG)TQU?#*IL8J)!QT?KTY1PL%NZm*CQr*v2 z`;R}v1nlJc!>{;MB;~z~r0l)bXn(BV+9NqunIRI7% z&9?6EWba!uF2B7#10dH^b@%I==^FQh@|Il>onfbV)dDbnv&b+tYGjm=!E7;bEI3|u zW;4kX2L4kM##8SP7 zzSgzU%8HANx#O{c)b%#DSpvw%bYqq<#w4xm^a zWIVUq4uXV9j}h$?>lZo7K+03mO5f#`zRe)DlP6C$3Mlw2JVSsiiF1>B&$05=h5Chq zI>Sg&y{%P;eVch2F*tDXxx7S55302_YS#RggG08Bjg8@qv|#*s!MbKnCcw#=Wa>TL zd?YXc$$v8+75`;ErsyX@Lg&G z9rv|@PN)d@@$F8&$vH+D%}9FadjtEn$gNCLxb`O>s}jo!3%T^Mr^nB4JpfMR*@^MN z(IQP1g4xXESHZ4hEGhkNs)kR|CsSV>#7}QMSs%Nm9ub3D+8d&zeEJXCmqi>w5Rq!q&z>vYf5Urk03dn#mSKc1%u`(l|_gz z&qR(_5%GRCk}iZyd9CTDh>tXO3chy6@xF;UXoZh2fnH&})VjY`cB~JmW#Ko5fdvN` zjx}9;J2pkwUW0v(M)a zA2W^Ud`q+~zfFM0e6F0Ga5eF^Zd_7(nRmS{LhAHl`GCvZL}t$vF=5CUYHK+4c zclQq!m!lu<7@YOQ_ih+ZYQ?N)xQjU|KlmNYBD|QMp62Grrl)3|qnxexQP{iBRo&1K zrbXHduFSlQ)xL8|6zyN2IJ2&wucnfk&T|^_*AUVxxkKWD@vALVqN$1(_4kUEN9!4i zYAiG2;Iux>Z2vjRnZuy1X|G{$L9gV0GkPN~kTQo>dwgba)^9O?FnT!$8o{z9GDd8-wz_NuC?iyoK$2L#Kq2zRkXZx)x7ht1QQ zXxlTYWj}g7C*NKJx{D7{?XIo;I1)s;&m;D2*L&P$?nUk`3cJ!PQE+x**JQL(1oiEDVqVgD%ea}kcy;;@McYqPt3;v&kd2Hf3?BQCYdhig z6Sn@(hgY_&`WOPyH7iuhNNp#tp|LUW>)`1*pLTXZOE|tN6B)2tRu?yu&8fQeqVRZj z>QuGsY8$iAXn&@1El8*BBFJM6#D>+a#(A3Iu;Oe=+Z7+6bD2SA&v6goII zw&ZKh#kkw7C#3Dy5WERmCU1eZt&B?1&3~PrFZyG=u0?jc76d833&t~pk6i!wxZyL3 zm+P;G+tOrV(W~W+{XJn~Juii|59(YC4i5hHFlnvP?Fyd?$ex^JTlZ!UVgyPNQv4jSo$pK2 zXm~m{$)M?fn9czk%N-C&Ar6Q0rOGDhx~~l9U-oL%Wxyh1TQISn_!_579NbvMMo6!e zvazwXl2M>6J%J4Jxfh zxr|hDK=T?G7w6v~U1)o91tFjuq~GCa3>ajw1vfies=oJ$Gs{AD-{Ub=0{@f8uo+Cw4GKf9r)EV^6AmBfvKQjq;P*Z^b?^}IUm+XJeTa8gn z#5(@0{x5m8a&T}Ek}U00hp6UZc+;qOA$7H~ZTPQ;8F^%F=%!0ED6YVL#nqFft*bPL z+yZ9lYbz^5bQ-mAjK24FT_p+J0-fQS>Fh!i31B;12G(0L22-x+Bf*H%nJ3uAw$A6L z9sobDTEC8-i3Wn@bzR*AWmv3to;Ekn1g-O82fLqVj}o;X{5E{&`|F&X(+YlHo{;i0 zD|2#k7RD?c*zExfTs8T&?j5BZLLRexP=^aU|4a1mA>Z1VAAmPpSSifr2qNJGY=h?l z+rY}AhlY#?&e!d{UgziIV`7H~0&zPHeQzGAD%FTEmS9mW8Yx8CzDw<*NAwuzSQ+TXcZnD)sI z`^OKrVP;ZB93f2Cehmln_ugxxQnt5`$j{+kIoH4 K&GPHFqyG;8FsA|l literal 0 HcmV?d00001 diff --git a/labworks/LW3/images/9.png b/labworks/LW3/images/9.png new file mode 100644 index 0000000000000000000000000000000000000000..ac29a72c579977849003c114626448a7fa3463ed GIT binary patch literal 62707 zcmaI81yo#F)9+0Tl3>9d5;VBG1$PMU5Zv9JgaE;VySux)hv4q+?rz^EGxNURedf7$ zt?4x#y3aX#*S4x({j2>xOA5ih#e53^0Rbx_%r650@mvtRs9!^Zzl0JaKY;(S*$ODx z%3A2#I%rwzK}cxXTAEteni^@px7V|_F|shHr=q2yVy1X+XlrX}!$wVQ_CMdCvamLw z7B3}`19y32DXeS*0RgY|^m>-VooxgGai%H4&m-rUus83dB)5*%a(oDLTjKRR?IV?E zz0!upjB%#Eew2Q#?t$Tkxw&EPy40xnY=N4n?5rts|Hz1Vr#g??r%xAdzF%Xn?`dC4 zq@-D61fDu2IoTe}ty>z@ZYJF}9m-?CK)&F8{o(t&=ascD-aWm`Atj_me0uZogJ0;= zU-;jM1b%;dBPy&-`1D4a7m)y5!TSR-4E@d1n}`wy2Z%q{YP@>&%CJ(Uvs%Z@EU2)s zaAh`E^sg^f3iI$h3&LXk`7=Y-RaHYngI`c^LAocDQ1IyylxgF}BElmGc4KHHLhCAH zx_Y}twwHPpDusVO|DH3AjV;f@l83C?jJrNjNND6r`BzKG{<=JaeruT25z8r&r+Dr+ z3L(nh?UVV_6XOq@kY^ti>13?uMZ^66?o;lcrdR&Nac%3m>wNZwCGXtU)|o0RG|H< zpS%%2|8!3pdRsb`FLUeWkpC~+fKmQqtTfaStib=3`dRIcEq9 z8M|A!)s9@`k6pgMBl@eoW4t3>IokhulaW-x>@RNo*;8?mME^NzUTuvdFeBs=Pt$W{ zfcWorhG`g~g#T--QUnb?mng>Zl**Hf{^xU@<+e}?Lbht@#RUKJ@&EN^CygT+L4T%6 z2ad$wgR8q2nWe`5o@la=@ZT0q54Q^Z_xw2%&Hwk%=B$I}|1}n1Vf`}+2U2(qJ|Afq zz5Op{9wFrj4wanwYo*Oi|6@#NFU-botLWQ$*niD+_V|CM)C{`3_`ggLfny?E{NIec zei&(QFrjhKm*f4k#*yEnq(8oI)R0nB!wwD(&XIH2Xf*!*E{%yE9Y)u{V0C{#NTpC5 zme1gGx~wI3dc1PAWHtc{OUxkGZQ%FsFB=*gF}Pe=Y&HidIfKF8f=Z#(QfIgO>({Ro z)oSyG%LSLK>+8rO5=zP-KO~Zq`^&|2g?tQ}FAx^Z_e^kbaFM|Ri0O|hH8m`*uC9GJ zK46oXMMgs6^MZs0|5{maJ(XB+IpkzApA*hkD180qjaJ7G1QvF7dZQ6Sh$u?cuATAx z=^877AS`D6g$Adyo$-L7q0gpfX3x;+bYCAIAMY(R#;2v>3kIUMZVjhTm+6UR>PTb2 zIBX3?ti;jL(_2|tEsr694=lS3OA7))UAe^2zXJ`cT1(EfJ7 z#jmeVEGa2DnOH5A%;o6pd~)247cGee`fqPd)z@glIBO-f3N z$#kkEg~#hPG<3RNZxlAG^>;WNHi#0NO-WpjJF6nK+Hcj>4w)-a{=*(a<7MgTUYJ7N zaWKcH@;xIAk-pR3UF%y-D~k{=H;V zQ`3^tQrg&wN)tt{yCc4VWbTmWW^NLxB;Ch{`-bxgRS2+WhyDE7!UxYOR~J}bPM^qT zx3bjg1%t`(!wU+2Wo1Ps4*40!*$`jOxG`uXKe&z@rTVXp@N-{tygh|diRaSNmvEzU z{eFCM@_>#0cpWXRuaen1$19yM7<4Z^!6bs<;N+BuIz2n1aHIV2;Tb$UeE1|KC8d>( z4S8ZV-Cw7Zaq5n-D-IHpjy382;yAwN{%m!*)2V)y=`=5x7%WyRFT+Wsx@KqNwc341 zQFR3VKGU=l5)#a(x(sj5w)^5319-e3pABV6V5Oy{Db?AMw)?=g_x3`2c69KAd8AmU zrmcwU-9HlbdpbBP}czQ-*xL0yejMLiK`k0Gg&N0u2*yGKUjgaq|P4ySsbl{CQ(z zqti(b$uq;@v{xZqHy_glgI2(b%FfC8k&^Nr5*AZ#8`tRlpF>=ld>fYROmu<&f_UP7 zfc=ohVu7P81W!sv2616wArOP!=lXOrdVpT13&z^U27}X?0RscW_HZFFk=-FGSnFj8 zu${E9?#M_;tm+t*)^bgTtSWV(axyFk4>&ybD&!R4SimLKs;?_W* z%9CMvpZ&F08-Hlz3DRh_3XA|JpRu~O?e&Qsux{V+YPVQ7SB-qTFFXkWffo+Dy_|^Y zI1#r{|HV2iYuRXGAF`OM>Lwk>6`jNj8wi%Wa;$ppbNrJEPF4(shSJlQO@$}F3peki zp{giNIyzV3awuUKjAMKAlfAXfvWrh*m>=9wsgu*JN1JCq`&QaSG`FsludZxOkS9V) zoDQSryy4tvA+flzBx)7DCGJgQAK zb0iajI*!@hJUzXO&cqp96r#T(ll?=?fT5u}<=LjxOgs^8fa7m0|r}$JF!#|#D=NB3h0uMINv0T~ixzw0`sL^<< z^#-3e`BY0gx$A=#J0~|bl**->FU`*@kk^!l8gx+AZ?cY-1NBjgR)K}1nufwiNIK|T zrC*{(L8kHUOXo%!wXkd-LyV#7?OvE^v|y=HA8*3TyV!J^7>$y~A99~B-I2PCMbT)h zzyvUR)88yJA#bQce9_4#(M_iRaGT&{wGnCTmyaJkI8A5rd30p6PWzO($!*<3`U(=c zWN%$CgGlALMb@a{`1+L~=TO+#_Z^ELw|!UqH!u?V*SeZ%1G6iWR3W+KX}|ibmS&|m z%p0D2pE=?u4nwav8YsLNz!@F#kfRHz=BGJXfS{Aje|*q}8|ZAPTz#JXV6A&_D)CFW zGQ)k9*P4zpPwzJJdLbwlO``jjUWubMWX=?tn4+Pt;gX8R?u%IGO4<0<517#s6BqRj z5699rr{F!ijY6X!v1BxqxJQ>O3pTkeWDbPSz&*_aw)Xb!v=eG!K!@3~Wuu^cjIS4r zFWxvBJP^OV!lq=yve;v`6ou(_x6`}KPU2uE@VSK~eDM=m)_v+CpNZ16FP&gzoB2bP zZJfjC^Ujq4ae6oIBv?^Gs*yNZC>-S34eov%bLXsTZD*t^9L`|Pc(nm+ri-en(uJ#9 z<5|-Dxs!2`Y_GGmIGb=u6IIT6yutTZommO2Yp+`jESyHKQ^ju@eztWz%DcOU=8cr` z!9h9HT3#{hXeT;$`rO`TBE5@I-7mcxl}(qOs_hI?pPhqH;w*oLgV&cfxx`RaeB97F zB7YcrERxZoT&^wJK4RoId99vf%zU$8gdMPbE>345Y5u#%OEUA+wPKT@|Ah^U18?l2 z@6Sf6?|XK&2OI+4d6?&%$dL{P8W0U%!TvPT=;ENJre^8jkPS{%wL053G#a9^xpE0C zR?j^fT`tpPa<8s8lWT7e>Pt&YwZNJ55()|l9sL&+o~tLA*qA{+21!mneSLkZGY8z& z_ve$EHjnq0>BEMGlSMdC@VE@hgAez&wZM5PEiZ5H?)DW4Ck~BQW#pb>!`ZSUD=-zO zc2J((VRgu`o+qW3EvRvvL)c^!=yNG!)R}SkvOHSI;xJVzs@;GfM$QS(5jj9TJ4ZXI z2OpGPs%md9*e{l{%REuGzJEq@WHvh62!dlo`NE<%53(zkyZd_#4o8~K&MxZyOtEOkvtgkpk1$&@QG2$^Y;UnSIVB~<#Jsws+N1%;W6h%=uL$-PHvXu zD+Fd1C1?A)H-^M;l5F;74j>3ckT1nvOY)z2h){5vrEm%NPn(LDw^ zpUzVAM80ZwQvQS@H9n=r1;>rYrJwxHTqX@#nyVAF37kuP3ud@5Nhs>uO6CH^JVw~p z^L`clrxCd%6#i|@?=^>+V5-U1F3adQf6=fH;7lHEr+z-zjc=t^o$p7TEQ@xFEyMR8 z3`ycqgh3lLoVqO}cQ@;keN$U(!3KXOwHoyPX^S7OkjK^WD*hQ~*jcO@XTd$rK*p%X zqSt-H92m_`ojAUP_4(5wn#|RCz>WmI$;sux;)R>$1x6iq(FeM|VAxx!(JC<}61cI1 zuW)uBXW?=n;T%**AA9_Vy`j<2!JL(dV`%N^d84VR36Yjw?ACHHl*(6Y1bjCN3I7&H zFE$WIIXYgMnOzzSy#3fHb~MiZ9Jp{{;0sGjOP_DH#`Dpf8KLTy7%K^{OQT~6Ez>t-c%{FtuWU`!25GVQyRll-FQiQCX7qt$ zc`|sDy-G_ac|%DB^G8Tg(*@ZhgRwcq?1XdaAv-fwa=Ff+;(=@9fEN$X8+|{h_vHQ0 z)oE+)^4Zo@vSZG4PZQd+h?EiS7S41jHqt0@7sgeCY9}tKIHxg9uwGmQXWjN?N=gSA zFNVL<5fjWKS_q0T@g>b0@F>$BtG3X@WHjyok>SzBg&^>O>+DP_CTqvPHQw(#U={7z z7Z&_(D#;65zA4r)@9pW)>WiTjk7LN4yTM{IRWir)3<`o}Vq*62EFIqh|Mm2gEREq& zaaqB5r$gQNgYq zS^2_sMvZX4w=Cw2!{Ek}q>d^{kF0q?tza$}j9U{26VqlcW+hrytB(19BlA3&6 zP-jU`70$;mQALHa$0S#Rjayq)))bp6-Pw+j#;|LsV5vn7kCLNr@>T3%5k$EiBofTc z&He7{TW&tjcF=gK(J~ctt-voNgoK8s=&ZQV{P=)XsUq>|({<^`JmY$Yc{{Y!)Kmr& z1uN$3JWK0hXvi0i%>5+GWt8z~w=44u$w`Cg`3kJtQQ*)GPcr17uaASM9iwdPOn)8u z_9i%JHK5wnaEuOqF{*a&wv4J2Z9nGDy>q-GFGU8!ac!Ex{k{#hvB()qT}lbL^Zs5& znPn#A4x6#aF0jYkyozXscQtykG8lETPQdXNbMUQO{APG^Ix*>hPeR|$bzV>$TJK_g zqDY;#cfBGlwRn(Fwr?Z5nngp&w}XRFZ&AJX8)1~^ZqQCf<`lHirc;&u98h=74(#-X zGS5XyC-@VqGmUm#lQ0u?s~n4NZra(zRZ-fn!!g@JucEatXFSh zFwll_H#vNGPZQGZn^9)$bE4zh8r1CIG#zzU)<~7UDHxupC881hYSkQV7FG z*5xZ9l!@N#pTv}>zXnR)v$uzBl603o8Yqs07v@an{0uGE`B87$KFr-WS)(bp;6X)e zZD-dxKc5KCefQJ(dGEq>Q*}S@VQbu`o7X&<4rPU=F@$POJ3;;umY?%Q4cz0!wh!Y-fqqM#irVNbosO{w$I&aKWOC(3snoR?Q4FTBy$O`5j--w~ zS@(_8j!Yj{qRqxVes0}kgb7G zKB>_)EH9)VM`Qp$OJ7^;QM(M67vGp3j8LwfD_i_y4+a|UZtwREb7MbK*GT=T>r)Jq zLPT3LMhkazHELit)vzaio==8i_s9XGBr zpZ^W4Z#ZAa`0UxU0*%JFBuJ&#zZ)()XOX5?}l50v~%q7n>jx=eFHX z2!&Bo32Q!lB{2hu5>8YP$e#R;q zMIA8ho4(qROe_9+Zz;!UakdJRu>kN@9Inr=!3tL~Aug zjj@a-`v-H~UBR!#6vFFDq$j-p@i@6Yg7}I2V}&ybqSVu;7eThRwmPioF+4@=b8P?c z%!L$Qi_b-{asLgS+vW_DD&a|kV5g2g9rfw9pFRJd=yL3d-hQk#Cz_9yhJJd^$4_K} zk6HvOcAYYMN%hu>Ytd8b0MI39EPUO7TORn5^Ysz}DN^=@g|E>^GA4)D>q^dJ30RlU z(a%(b1KAv>5{BbjWcp++?UP+>bdEYDzuNbkUyi-^;gTB@6OBVF><2-sTi!8EPD4YM$>$u z+JI>(TWXg^UyDL2NR%qE>5GyMRbnLp!8oFj0nYwmzy4YR%UokbZMZ{nD(M++oPTx* zs%MU+DpT{&D^C-aGv%ma35OvxW zTJ4Y^knF?hl89w8!vye-)&YI;{BLNmuZAahZral=wo7lRhJUXi-gMknZMZIn7kt0m z66lcT=rPC&j$H`iK>S!W!dRQ7* z<4UD5;j4vLx+0w4aL)}^bRH5omOdTb^fH`Ke>RP09;p(eTC~V%U*mG`!yS7GE%ri; zE2O1M(x58Fl+hV~V5V$i98y1EdC_>qMG@%|=~D>F2u9=k;C>4y+SF)ngw!gE1;nrA zF4C2ziwfx^_;T%WwOlAo4^RCG65dFhhIOj7fOzF(9OY_{K#tXjf6T&ydfa^OOG>3s z`ej8u(4~$Xukeh7q<*jZcRmkpFBcbYpPq|;&_T<0gZeT%b)*V!hqDjW6F>c>8Eq^r zTfnrO(^6CHg=58@TW?!l3^d^OQ#7q<)?|D3wbtLXm`1bnAzAIU2A)X#K$lqq4dqvG z$RD>8JNOKWL%b(i@ORjpFgT8Sz0o|BG3T6wsUB711WvK(6n@mEshAb~k_s~BTQl~G z*)vo3_W1KHdWOgihfUyta-hVq@`+#e`uD(2yKhjqo1L=S{NhNi|GAjhr{b3@Eb(Wi zJ$E#=eal{5Q)&{A1(9#Sl(Ooje1@6Ob-|eAZ^6ChV8H9%tgznK5>60)I~5gGO?~}nwiF(fdfm$w5O_)F$`MCrN+z&;70p~ZS?}GOua8C` z5d0Y%>nEDYn<;~UjSch3*_jPM|+DNhXTq~L^#u2*ec zY}rtp6W{K7BrZ=+?XbE`Inqq-YE5VOaBxz+S@gt89yiETJ(`^?s@VIPFD!Fr0d^wX z`;pS&tvAr6itb*Kx`(=VclriOF|1*6`B_a4j9)V&aht20uy038ZR1)~R<4qRD;n4b z14A*K7{^u)luZ#eHL6~1N=}WgnCnTdv7HNVXy+i6FLLy3XnGi&M|qv?cx0a0MgDH# zoDcU48YwZ{mu7mrVYe{5iyz<&NA?qv<1AMQ1UNgEPVX%^-ib&^d;#SiZT5H^xnQ0g z1!)e2LY2(e*z@K7HMJ7Dm*5}?tjj(|h3ytdW>Tmh%MN_UfGP zjGNBaMegmHCOPkr-drAr1Oz~H-=85NARxe?(|DTC*B$Sb4=#*3gXp<0OCr9cs!IRv z>i8)^@&XD@&N%rgoPNrc0U(0M&CUIAwF;l)@!+&GQ79II%Son|1t>>bTieK{va)jI z%tWQB>aJgxbhpqg@9^#?vu9WfXB(Fmc@KNgpH@?{0e&!5UKikN?yVW4)IWq%Yzv-Q z-8Z?buPQ!oX=?*BS+=OYC`6;U+hKS2bBqN~K)sD}1ubuAO!0|X(qP^pwYFJ03AbW@ zT4)o$CXJ>`l7|dHBI@Y9vF(^?Z6=cSK5=Qp%?^y-{}2pLxr}V3mC=GDOfh-9>bkC8 zCk)ao18$6-sLWz{#^Rf6j)yaprs=sKX2}d)&GM)^S;^@&!ktNYJF6>M0y@PyOFx9U z+$KX{EpDwGCgnCLxLfyzaae4`V;6^2Q-w13eoZcZXAxZvRZLSU+ zWs91E%1Xw8fq@)3vWA8R(QHi#H8^aRPm@LJ&!!rj=()JKp3cOtFQA@(mXqrMKAaG6 z;GQ|&Y-eAejY^4#i+8lPeg!E)YrytSZx5SK{~D;t0%bmcnjoe?){s)AV(DnP-F9#4 zxXwdXOY4JJ6vgtSrU!r=R1geCBi{k#I&Fo*Q=_L<0qG(zR~nYN@(XTnvQ9reGAz74 zA=+uckx*TyWx9Hs>!)yclj#y^wwbKofYhlfi+M7qUMQ`KZa6_4k|dR7vmD_AoeiEO ztv>O97`y|ySpIc2%+b~o(@(Kr>MjcH(WUl70F%IiWv!~+dKl~~-i6R=&gueJthft% z+_n^BJ_6KK3Q;M8u|~@nNqj7O1ZFN6sXsB4 z=^Y}~35!CmGd8CLcp6zFm&bJi4(@p+%v;gV6tpK7<7Icd0my5)J^c!+2g-dbv_Vh7 z*{Cn}FX7U)YZsNsf#S(rrRt%0oZX$WZA)eR{k@|0X>}p5EN_OhfR$^w!q@D1sd`X) zzaKgUj8~{;AuNw8d^}q?l3Yn+$LTHH9u>Xc1QZW#FH>Y)Scr-?R4VJ_<{Iy~D2D51 zDyNV`M%QI=va9bRhbNgn5a${7bcu$FCE|~S{mv7lvJ0rSRfr`sa`uNEM#$Pf*T&!9 zzWIU=p^PzsjFwB5kgfN{2cLGH%&Tn`9V0{A_VngrUks$|l&Z~fKn`x}+*zgCJV+s* zQsOg=Pg(sC3W~hC(b-OBalRaxy!U7kvB~%c5)vp+JdeB3oAcfH27MhJoBnl>wJo~6 z=`SlC)w!BXE}YE$EYBCfpc;g$8k7Wrw%`MsmCRZzTMrJe`h$L^*u(M7xT7UcTYy9M z<96$An30Y0i%AnjUnxv%G}xqleG{Ow4H)TYvbmtP__!O@!*1W>!Z-&o7gfT@P?L-O z_Rur3$geF2tgh8OvEdokW_)j5%T_ShfstV|wA^cRrT&4R6S=L8nSGTupK;z@7^GM;ostwwU@!8yk}?FE1CURtG5kx@u)-_v+*1#jlx}nG7q2PXVZuAE~G|0B6gLZYVO(2O05dYzw_fRW&tnVPRn- zyN?_k34wtyDiwxS?Pe9G(}-ADSZV3$#ZJ=&Ybu{`03!v2-SI}MZ)s+*@{TZHyz zvIo92y2S*LFRmCU37JOXLNxM2q{^QI6QO|UTh-U2tm36&$jXR4+-9)RYwpxkyKXgX zHGjWm)AlYsjj>ZoxdMcZAJfO!*ZrYuN+x^QwsVWzURCNgF{f(RxHjWNh9VS~mr^8- z{5mH#V>M9~>FApn0Qnn<1`eH*g!iuJFw(CPR@OuHacHF%%(JXd%#X_X>F}NRiagm{n+p5kObeJ)s0X=2pP@R^$geJrT{Kp(P`ds zSv4YFuk|MLT-dL=ZCF64x|<%Imb__%^S9~V8TQq5tdydo^v~?B{`4Pkmj?8k>mLiu zB66SCjFIZ!>=@2*`1kZyy{GGoVjW~$p27=e)=>K3=9~SzSf?Q1sX$ zy8E%|6AP-R`s})2R#K_)$A74JD!g#T99AFhyDXZ)ZEM{ojF2z zLP+SyI3KxZQJyiFOShC!Q>p8i>lGxZoX(`3otPT{2@b2>P-<7_-)p4k<_|+D?#s-@ z0w08Gz#h~MV3RRXUh0op9~uX2|4O!FJu#Ty9Vow@z1e%Hda&E1Wya{v(I#u>#ybA- z_#Gsb5)u=)bKT#H$)6{T%Xd*L2FC&AjI$F|9Q(@;#&~x9Sc<(P?HqoKmB_o5cX2hr zfAJFgrNR8}9}o3HU-XLS^k&l3C>J>zG(wwsL^ci;-alayV-mAKG9a(2eG2h`w(1{2 zW$hn|GREud4dvJ%Yw_l9^~e7*2P0SYe<}AwI{z)7`wtD?qZX>&T*+s02fT!Md89)z zCVY)1=UREE>nq+^Z@IIVxe%gGY zE3+V?`Nrw zE>l}4pMXoS{r6Io+G{(=l-(D8PY!Ba<*%-u%pWNR>_}D%(xr}MBXzQHFS=tBH@X4m_}$C4;?F?K-O0} z>Ii0;Q;ldQuphB92`;iFT905PW2~thI{DQtqBOIxkoY|b2TiD2W1GP+E~M&{#1<_S zm(!>(If8xWsgm+81}AeIuA5A08I$E1yun1@B@sdAPF0n<@(WFW?GEzLy{if?yryME zwnnFVai2zPkx%gyXU-@Ho7gezb(Ax_0c0VmmrIV$@WI{X?jIne(HKmfCVhW$&p|la zjFQgS|E5#k=q}VKP#!Ayty8-bTUu)CLKq1taWagW2V^Y2NP005u#_(r#!Zx3#LB5g z^Z1w)CLnnqESDR-n{+c&$Waw{gQqz-nTD@8PbsvQ#Uxm3dNbRcNT~eME>B4tnoFLs zb6v<$WbHcX^Wqa|25rWN>>NFOgVgr}bV6HvGEFFRt8wIsxDnFk5eo%lw*rr6PAg({ zNvY!mR*1!}Bj}oEzel{ft6mFtT3HWDQk5OYK&s|w(_Bg;2~R(Y#q1C9IO*Lqr?^@x zTbX5V9PqPAX16|!&#hq?4Rh}D;Wnt(+0V&dA2NmTKOJ*ikQZLx-%%ZCU~V=;7EN}ta7HjH~qthc8@Z@OZf zhHV?Ty*iQZz}?{)JFD&x!i=9?t0`!GZE?FI_bZ5VxaaF*lR)-HWS@9k+M zWmffeOwVPqlhs4T3y}EtkqXj3_W9h!fhnxj^oq%z4b|c`5q@8i@*vh?KAMK#hpTp* zh7((?PAcgs<1>Dr8Nf8yPbUS`Y?_K1M~oJ@q9eZVh?J18EK-Fm3}z!D7@Jg~KNJ#o z5t=6v3XW%h-FVWiF(>CWdH&90sFQPtUKo<8GR9n02{T8gJP~)9((0($n zy9553L$>j(#)uUbCRa>|l+^0t-qib$A9##}$z<%R78kly5Yvi9>gy~GV?j~Wy2JLi z$^vb*B36+dEDnyIJ*Oz6@g@6PRzPfIy-|XM*{$u&8QvEk9&de;BD>9jx6dkZ+JZfh zXqgknLZ+Qhs^1l_RiLpnm_jQ}TpX0-6nedM7qe5F^{n1#q|Pdmx)F+G zh=Zn{ftHM-?b7|-sO-tQr=V&N?tAeJCZ2Coh+T$>I zkW!*FVla;iNIG>0PpWDo9XW6RfPgn|-?mLp1G(nTlb{X;Qb(_4a&mHwE*^j#kRf07 zBS~smSV#ha&x@ljEQ_V>ZNKz%0s^7njFgm5U^BiH-rxmHBRWyHH>t7V^m-964S`{^ zg*O~CXo!#1l(C^*UNSSRu3_<~$V9{t<*v zYl3YDp=*Gyb77L`8(H~v^|lxBH`reYyHrM3im(N=YmD#aps^p?6OlaXW5pfpM@Jge znJ{t{C?5CF<1cZR`eD0`oD_Z1j@2?1u(pmJ>40mx863SIeS1q>dVbjKba<-+lWdKF zrK(=pVH4Rk97Cb$c34nw{>2mDY+A}TR3V55zK~5<(ZuvILk1(JX@^eJeMw}@sUC|u zQegA<_MAt{<(RDgjD5S%uZApkOd|&vLu(8=&Pq+Ztvto%$)AE-269 zVQEQY(Qph2)SPV~oCNw#B;aArRGK_7wPg1j(tO3@EFi?0oHqx7y0^D?=3seQSrL6T zDWDK%xQ^ZyTqeJ&Lar^Vd$*jvInl~^=6>26Z7g6)_<}Q`+`&HJCPRbo3UHbFCmOf|JZPVj=(3GW0v{`C( z_oKMKB3!+h=ToboizLu|R9l#FMl`|VymmruU`l;893412bL$1=XT_93q&&*(dH&p3CB9o3re?V`*hXv8D6@9c8DHwT8^=RenBU6FlYcfYGX9m=$B?U!Q zN-O!b*yA@_wnzIUxcUL9-ALOECW(U`3lD#Qv9@^Rho@ABpESzJ@v+wW??^yZoS-L)Bk7lgaYK zm|u`dAgm6-6L6sL?M`lz$wx~6mCUGivyg;KE@Nq=z^@X+=o?+9y_wox?6Dq3z$X$P z>uF$fg!M(Ot5J{b7|N{nDDnkPmcE>F0}`shGS*K`N;BW0>|n)bI{NCm13C7{M!lNa za?!}2+!qe|4{**Qez0r`f5`@+EZJAs{2~uT%lsn#8QSHZiz)V7*TEf=+{s2>zo`rivXo18)3|v8@Ex_4 zo+e@#sQAFl?!2Q zId3+HgFsRF3$G`wuR?*+S4l-Ho?FJeZYj zGcyD`kZn2HA7mWM2saA8@+T2oMdcql{%V^AZ!RGEZJTI9=T_bE_-nnTH6^d2X~CTt z7do$NAYHV!MTT8Bw%QKz>2~XA<|qY)*4P~RnFp<(*8I#zT)uK9C$Mt#_XjM)(PwN2 z*8P@A&y40IO9k&7WW*zhfcs4B7m6V-Pt6G8cvDmJ{cgIm@6hL1>#^ebi!>n_S2OeZ zyoxEj=f#H=Gi{#B#BAZL3?BtorPXF6xAO{m6&PxY$uP^X(3@%ei$XH!fhGpAIK~~4 zDq;9@hCIR)WxxyeATu{ihMw;7rl=B~-wX|0$JOMkH?hQb#T0OxqThX}xh_6@=!%Nq zH^F3Jy1(7M-9S3YHgX{(${i!xcO)CC@TNVM5K}0lt@>&OjlX?kiAnEUfq(qFve`m; zyNj?&eN$X*F5t>V>U=-jW9BrHz59`2AENZC9D471CTMU}WwYJ-*>n1&`T)$Bf`W{hNeqAx7Tc|NU~(}k`-U}L7knUR z!d{L=Be=GyCV5s!=VaP~qR^~hFVfYT`x?IZ`5Z@}!5OS;5LED)oXLo6{^s7eLVA0> zmGbOcYCK8_m31JC;ITFx$7^vt7~EXD9hh?2wKU2iqU?*K-%UKi`aEG+OT#B2+3?Cq zr0bHIe#8-?JU^XJRxw2MRiTi+)g2DnTpSw4EV`SHl>T?3%i^Z{u0gPntvs6LP=hZB zxP^jDa8@6B`m6X=bBL*D!!)ZV_0HxD0lMhvE&bwZiJU5ggS;CWm24m~CNOG;1~A`m ziui|dXS}3j%h(^5F8BkiN1vPdF&PGQj>!wjRMyR~xYp@Dc+`X;TX=P82n}-eRP4v} z%!L-_Y=%n>HuYdnZwe~-5Cy%k#-L{p8}&`B!7iFR!bCz994WVW8_)&$Guh-gX* zmLl61iV(r3C%BJ+Jg$0Be{ZhWwY({*M@dM&A6RL&x}Y&FTIz#@%0?&2};qbWkeQ7RZeDxL%Kbs+PfFvwfM?>TQmkfeGaZbq``(awo;P}}R$`sGl<%N07azvSNYu>o_J=cLBpVzD@*Ul?Wn?+5_`iud?Y-9CF zO$-o^Cut*qNR+BoU$nGZYphlsf#4Tp+jGEL{CbVNM_j04iSpHKcQ#^mFf#lhJW`XQNT~o5PO`|ri znX3Ayj#P8zlk5V-%b`HP9QE)BoJsP_8=xwZNYW(7a|7(e3A`k-8m~9vt8tQ_=z_WU zpQ_9>RJs-kyN|Vz=Zk*2L$9911^Z{F}mP?2mKk$IiGtP zNB&*h)|zs}BIvO7>AzRhb!>5qCnx!7=;^-F1VtCfmkx(7s#uHs1)i0F>J&A#ViX8iyRx=KeR=W zTu_vYjGU7*5nQRIr`I{i{U~l|_!02RmhtgQ+av&!OP$Y+7d#%_K=so1#zsz1=#mE1 z$F@m80&97(r)+W;X_AI2OrB$ocbbG)K4uh7KuP=^|j#AuiF90R$gaFgus4O8n+hE%S`00+0F;&AA6%`%*{e`wk zzkiAuf$7IjDW|@Q-r3Qyw6-S4Hs95iHP-;v8L(rCZVw{FOtr-z7*j`(e8XTejj`rY z03x10;-A3q@bI4Ww2mB&M&}AsqZzRpfdEt>b$qe3zW(Zywsu+%ho7HcX0g*#5ti6J8-OVlPtRS_$Y$1sxr0dMZvg2S;EeQzv(~L2XN>PUxSme5c7*)Nt}HQm-!qO;2*# zz<|T!>H{k3U*PrHQ#4ciWUZ&+;bs@qG7i^R>3||O-|A{+DXwe6F9kH5H(TjXkQ>az zWKd}cs;1Bx3_oYOWPJTo2ghG17cSV;1Sshhm@zRR`vp$&G^^FF0+mXCFv}wTdl8nl ziHR!PAb1i8Iafdmk^*PR3S^_1|EaE{spoRL83F|mCQU^$xk?p=2;jDL8yx25=BCqS z>s2d1{|tGKH_YF~#a)w6*8kt)T*llWX$gG4&=k9F(7$8b{T%L=`kIk83NQf(6OelWfxpow*^-bv3qmYca^3cBdSIiZ8ioOS^*ds2UPe zLT1kq9jh*l?p$SaR^tZmQ%ZH5VWQwzGK3!gj%%|Pt{3zpsDeDPyAoVg zo@Tg6S&agM55q*uPQDB)w;F9QMqB0G8@BcRcQv5yZ zg1=PM7y;7=WaL{gbb>%xB<|ReoO3#U>J=0ArT=C<=trYzfaojub1Cfym(ABZlW>v0 zJ>#>ZLKe=5Zqgv(4|%_#s<+Ma^{)8!=M#IH;xNgs3|CiX9@$Y_N~il%KKDIQ>==i# zmQE(`STdJ(=j?>Ey_`E1Oi zU#Py%Aej_Mui*CW znVg!I`<>4);zUpDZSpB;+0NqQdrpJMv4(GJ`QxDU%Xh`3P@y7m=2p|qrmqzE^b2Y{ zL5!o}aO;<`ejyHHNAWREp&E#1^1odYW}@#p$danQa6#?%nbuD+L@}ihR<%Z~VrQm_T6Z5h?4_5tJyML2oi1l0Y1x9`f_k#wifwn)v zZgWGtotXWSGPCbh#%!?+?!$aVTba=lbn6@ib0V*1W$?3W^6lvEIfZIf zAV?i*>FDr*g59TLSqOTAfsVyRydXh7aB9UcTi^-^2tb%lm3#%FDeIFp5jipxvPgeW zb`i6GXgJFnUnmrEI&6{s#`&Hun5t7hK%kImC|#3{36oRn!}zI=nifo>Y{~c*i$fcz z*4x9eTU%F>n|`*qa>xPmz@*fi^kbi1dMYrab0wQ%H1-U#Aeu<_tb!g=bC+!TppdSc zs}6x&3LChLhWOL=Com=+Z#GLeWh@#}azZn-GfJk*4W4QV6pGYD zE)VAYLP9p@YC%;j8(SF=J%W;RRzQA$7@=)=I240k{|IPftT*~Fo;(y#Z~WG?+@_P; zA3!!_RMaT0!Qa30ESpqO$_8U!u&aywC{5K!=k*z^Y1_pbJQaOJ-8vt45b3XW;>vGo z{!tl}bf?A`Ab5l5mg+oWeXy$5@Mjd6rx3s3xvGj)au3^0VTjd<4 zyelm#x32761d@Q4+UI2Ij-5t^5}8yWIr~&Om-GfT#bv}5ip=I99m_A+;R9`FQgqTA zt#y)luzjp;3k|L;Ck4dYH1#w{aiDi?@d%ZaQxdZc#9~-*iIx`az%?~J)D~Rb@lU(I zH5Tb3(pjmrwT9L&gweT8Z6>9Xkyc9CsPv=s3#qDaRmt}e)%((y(3=2jMYzK|?NSZ! zP`P6AWji zqR(;}E0ff7pv2Thy5^X1ZCt6{ zu7ZAF%vYe$1HX)*q@uELwBZ1hNP5d{-v0MEw@uXKx0-O1?=bYceeSc3W{KjFpz;nO zT>qBAVASuahpAeURJqYtAox?V_jM%$YEwR$cL z`mCS@aaYvoGv!dDXhQGkzjix}a^x)}s)$mAjfoNZu*hacQjKS*F6Q}k345V)a$LE6v zGbswhqrOduUZ5+})D?vE^I=r**|aX_PFe8A@|0HhszYH)n2gk4cEbDf+-3oeZuge8 zFYsu0ob?kkU<3uiL$}@$af#@DZ$-2-Qh+D^78=?Kl(v(*x`B$rr(ywM=FsqPJ}WC) zNlE5p!@eZWcv9J{h^MLF)-6=)CBYj=2~^aM%w#ze9XU0^5_5X1cDDi9j4xkq9IuJ> z6eKCTK~1dS+ife~c9z3kRrjPWmN+iNP9j6FyWkYNVGFtkm&&A(7uDsDLo!3d1c}cg zZ@c|}e4TYzRg1Rvu@wZBZj_W3=~j_0k?!v91`81+1f(0JyQQVOyOC}Lr0W~Yz3;x~ z+;i!Y7_O3EYxSx)`G^}SB)^E8Lz3SnJS$jEE zEH?LKN;&|p!-+G!95rX@SEPAJdPeyiAGr5Ln7#bS-Mh9$cfy0y5~Wp3Gj;*W=Kbd_ zxB4UbzGG3}(cjctW2Kw*Nxb9doK4h6A^)w__Mmv{i)8#VhB9+)TZux(r+;%yIWrQZ zQ7DI*uH)MFg>3~IMo}lVGflr#7=w0{oayzK*r^inO32jewSIX-r}q5|6#bA~=p4>b zRW8tJlC*4TZoWwny=J<>oG~D#s*9IWSltxWenFsXHZrwzB>7ymPE7>e14U|X?Htj zn?3(q11E8jN9 zJKe0Hh#tQB+NGN5U`6osqI!^fWZ>dc>xtrgmJhbJpV~c21{Z?itl? z$j1Fo1Hr!q@|d%S4dJP$0|oDxuZur29w+z5?;UJ}=gBAd?*bx-dV*#MMFUEjyPvn5 zpEDaxuzGX$$j>OR{mPK}aQ5@X>ljpgS0dii)ZS8AY+Fq;pXS7frgedWf}y=y;|n7~ zJ0n8BZFPev`OxAf8jp6oXvMkwGoEWx?g!}&CEO%RZxVt;cf=!YjH8|E(;C1G; zLwi4R=8mv$a<2HN-pr!qZxm_Qmfk8ymynr`ed4NlqM))`p5U)O0)NPOC3Q3y7jK7&{z}gz zu=pwTF09eU^V05}FbgF@sGLeFq>E0Y39=2N__Fq`g>yG3793M~8*Vl*e3xgNZ8)4hCtT}Gh zbB44iDH$0jAWBg2S$_2O$pp23@tjZ#Ge==`=QF6;dEE)24QImuM*ryLo!&Q?8?kl( zGqCZ(5(cQDK?B~q|Y zyn}PK)4hPA<=*#RD1N)H`RiVFFIy=Xzbxi5c@7dMCSWd>hjiaR)rh(k4p3U+W5W`Wm(_Tu0Z*cJ_Sk?r|wJjx*&Wce5eZ z1?yLL!pOQZID8R869Yp4B>b2hHk1r{;<^Bpa)gR6~ zr?a-(YxFH+SvfD5`ktYR1%vh`f}Y$C!m|ySEeJ*ZXoS&|2|^lM-TncQ+nqMf3eAm|MxTffdB(HSn`*sx-^MykSh$|}Zpy!4I2mZk?00`yE7+6*ybpqh2d?n(V+pXz-1M=^S7 zP7YI{{~5L-1FbauwNIbpjJx707T-=IMj4?WLKgkNDNn=X0;zb~lBc0!UQ%h5u}%m# zmJHEdnt6e?{h7Bkp}4F2E-CYWp8ce9!bDf@)vGr-Ip*?Bq<>6YI!_*R2Q0*L2`x$< ziVdvVRUM3*4(4f++`4s(l#~<+(Qm-nZ5?{+@t*^$TW~R{Kvx1$Wi0?qDXFT4OIbn= zk;MJCOz2H2#B;oGGk;p&s#t9_g2K=3=%+UVeT0JYxqlUr#em9O9zO>0?Yy+FSY;Ce zY6T0_iIa8^Czp|t3B6A7=NO`S#mG~3I)lKlx;WdDhCsF6({spid;?Wb9(y!4-LNO_ z`puh#CPOr~-Zru-j-5-ZOgn#KSVf<_lB2Ax!n4|V__}uSIMe#s~QStX&XjIJ;xq9-#H?5k0wgd3G2 z>E8;$VtO18)@1x~BWgf7znMmW_!cn(`Hs zjHcNLsx_KYp13Xrn0b}vpUo)9o17e4%!>E4R?$|8zQ>;~H7O!am*`42gSMOt4 zbS#C&eK_0F8~)yyQ@$#_2ayvHL2=>t3a;;(ixboOhK8|XV+{VYU+>YGkiEuC>|TB} z9xbV6*yFEK+S+$PMN!(($E`KX>PVxl219B>Q0lS21T@0cY|GKTTwl zDk-kBB~oOD0z{hrn2!h^xQ=0i0JIk0cy`$RU@(t}CKN%iAgNvz|1F40JneOzzT!ir zcUTifG%dPxbU>urWhBnBG&hV#w2lUiz!Xw4o6_4?-(jmYR_BIMDq-OmUpZnWPW>aE*=o0)_4o`>7{8h&6 z&$q_c^J+Uk2%q_IY1+D4WZiA{4qmUtK%8uOn*24F7p~a!Dv0p_=*-Kxm0NQ#&|ijF zg953L%!{m{C>EzYnn$kcx5w6Px<ull`?kLI~Kc8oAYZ$<->AybBp`|pGqOw-ls_eMSY*X#2Lvf zT>{19emM2Jt`+&z81+Pq1-YGOuxn=1p1QRN(P(;QXUuS``Ul{3bQie1<$vG&GF&RK z!l-AiO+UW;11>jP&1T1M_8#g3ygZTCZ7J4VbX%h`<0g~;&hibfG>XV=gh}xt+`}+y zkpw;&=>7->j4-kDw@lrvJ_MeO%kD9B#DiIifmpN(5mg#WO0C7l1L>Nzdyc58z^ zFf@zmEb_ecKpbadV*~6J+TeX&SPCP$>*nt6yje1W3kLxdpC2)A1=j@&24orn?&;kp zFz%R>{AtGP5+l$3Vs%%7}X^ z%_lnu_!_t1aw2t|s6=yy|^eZatToakjyPDy}{UY{24(T@1nmn@w1G?lyl_v*k{nI*}L$0>cK!=}#m zbTuJZR(|gTOb&)gtZeHYfH`qZ@tib!g8eb4nS>|hH$PPt>Y*zxmyLX z#b#P?v(GK0Hq@g(4VL^Ivq~KX?vUJ44!3jL1C2algkRpBbuOoMMz2)bvd9@mQLe#cun znVvdSLhn*p%GcJPC+J>Zc-=T_-FJ586|S>0De4xzTr^*A?D5^rSJYBXyH7+jiBY6v zMapgO8d%!|k%jXW z38Z|y8Hh92UwB*ohO>-EQdF%F!2}g6u~LaoABUXY*mY@Db{jfoHdT%IKX8-MYq*35ePasS?+W=XrgnwyxSMf zVx}>%Qn5FTt;jI;onfha9O1Q#Z-Cm`7ld3gF4&^`ho4(ZwxcIl+$@Qy8!40uq(+hS~|MMsj1QFpOEN} z;j;Jbie?Y5v3P>pyS@*E&Hf}o6u?TaST#5yI*zZ@vSRTF)4{wf>#c=sJ8|F7auC+c zc>*(!lp$VD`9goOrXYj2xwvW<@~?vVGU=6<m3z`qGT)uI1C!ACT-=?hL4@-`Bfs+I6T##n} zV+qB?LL^hFYy4B|Qs*tml1m-ZulJU%3@68N`aHCUJagM?EysQn;I|yuQ&2I7OJqT% z$9^++ zd_NC1sTC5(oMlqSNFZY|I;bQ&z}cl z_)`*}V+=4Ko%o}O_~x8^oE`Z*Ur&t+VYhIHF8PeR*ByF(R-(!e?4K#558lkq_Qyi^ z7huZsL>CKE=&CR1vUD1DKfMczn&^o4Km_MEEFVRQ9tm?Z|EZ?CmnON%BLoxAxBpIk!I3VN;k9p|5fkA0}`vFQbN8`9p)q}u#|l@`X;Yi7h3;O~D*$uH9t-w@O1v~JAH8(v>r zc&?{fX5u05EnO}FgKhGr@G499VB-mOAH-}!o^{U~>1;K>`#>7MAodn$4Y zE{xxfI;igGDI#A>S|w2WV)ER3G#to-{vn3ImY*q&}uC49(=M%Y{ozA&ynT1IwlXg14YcJ0O0jgXG zal8Hwo=1-!Rh{j2&}r6GwO`BjAtWTk<+LG(ewCElr=2Jl8Kt#HLWPpK**(lCfjVOA7G=-ojvziXetZK0yJCxDPR8+9w;Oz=?qs0 ziD64nLe=2``#t*dG3=LdMTT3S={Y@qc(D;N8xtEG_#HiOC8Ba-L$?3IQkvFcwHQYd25-EL~rG^29_oC z$u3UZ(AO+o*buu_97)5nZ-3pdEqN@za806LQ(-|!HJAXEdz(GyZ2z8QZtxKpHzN*~ zj)M=of?KUnZG}tcjx?Ly^L2II!TIhNNAwnKXb+Y*BKLG?=X5h`-k$JJQO{InMU`|W zI#-$@@f|OIYBOyhSrd7!wqKkAaX&~2R>+;W{Yy+RuOuP~?6J)5_AC~}O$+*}Fwp6U zS&p*WxVKlO7)ptijGS@zW&^5#qrJUg3Jo`cy_oX-JFd96u7>^oB~-lMQc|dK%u(U@ z)&PFCqm%VKYdbr=wZV+DqxrxTGEE#TtR47dk?{bfj;=1;lF$G{WdKtoD4K7+fi%Js z!)`*T@IKXPCBWQ?=X9f}>SQhJO+n=a+@Qn>j1(0V6tE$BKWWK&A2M>}sG-`AGmoBr z=FFhA&L|w8I-*tHJn?#oz)ja|%I$SGquy9D4Y#8=an;ADQcdi5vTb$S@tuyq1J~oQ zzfnU4=R>+5dVEJ-O;CsTuI-_GisX_;BH)*oV_;8ZvT-4td5;@jp$2mIN>T{{N$}Crr|56M;Zx*(>hMEJw8BMJ z8S$J?+|U)ajY_lW<3SmwwTFcltNGz=Ke;e zl8mzJs6)I%FCt`9(33-H6%|bMX+p)&lkpp0eQUBxLnD__H<@*B8{D!$u$L^i`w^)0 zcin{L2p43DC#|jbtANDx(aA@jqQr!1a$mtwvZ{OGfVUrAbXZjW1=!zuCKkvlw}-qN zYBMmk|A#<-k@XjqX%MW1nP2|djqvxfg}E^FWd6&ukmY#KIIz;+Cm=xif#_kN?Z{%` z`176$=)bzKrUG$oB`dEcNik1jbZpG}?8q91d{E-Fx9yDkVQBOgptgjBgyb9lY{SsT zhR2{uwFZK@&A{RIj5K%Qz_^V3S5j!NTlyyx3 zIpW*vj0k2!G`OlSL-u-MVWAhqK)BR@{j|-W_^X=j^6myKqaZg5L7DJE@< zl_uhOo@+=4ImO}Oh(i*x`CRT*Vf^%O>M3a?ON%=x=F4Uwiyo76by4O1S>!jX(a>^o z1&+$37ARG9wq+zbu0&2UKf;o4>#Di*s6@l@up{T5Mn<8%Mx2AP@{|HE@5j6TeK-CJ zzBcXBg)|kd`RtZ7Q-&!6^7+|}&Z)H_lWPbTcU@Y))&65r);eE=J$TWa@!4_Z*Fz76 zx6|)2ewk@)7!%sp1<;$i-9B!>y0uKI5rNsDKE<5AoRVAm$|@Fw!^ zDfw52j(8)O+^LkBDTfw(!cQ^}SF4$M<-JG6qNIe6%SRhW5ik5CQy9tX7~8<74G>Io z+4Qw;Tg~sJ85BHD#IBVBq$fkB|hZ1*ZX z15Xtlu_HgdPn!9$eHhMgfXh|ylxwr&O5%Yxd^k=qWz+!Eegt(noqffN|&pVJ3e4;>fCLs0fb{yo;tCt;>)0D^SZKl zCxAnEiizeMobL)XYLp5>IP!#w>9X4P`o5{RnEsD0*$!b#aE!>j_jY^)4gb%rME#w{ zCEu0<>D^N~um4i+L1?eIyf~G~$USelIGC_3!}{{17D!M8egEbs>XgO13v^io4XV)m zjWc6Z-1REfB0SZ5-m@cI;mpD@z3cLTwTbQ=*bid4I2((7$Ft~>UG&sUB95PT1KpYl zUy8)`T7qD--7te`*YPVHq|%(j`L?JGxlq>Ok?2AI~5@r+8vCR!E_e6Q^UB8Ey%_(Ym-xc-i(fbVe0%7lO4<{RJ9s?Cwv^48lvUQs zFZ+}nJhvN$#2K~I)XTRMod{!!)8%e%xpJVHn)0RvQrjAD&#(kg#K%euoZDSuP@AE0 zw!8Aj>m2WQ5SM`hOyQ(+?eC>#Y2 z>E|D#er?C3J1W+YiavN|^y%8$sltqzQ76tk(a$_8Qy~pOGg+6xek$e(!rPeOqlEBj zwiU6fFp)DS_D~e2Jg)Z{-xL=lJrkpIadXtl3+q>bZUz_FNrz{S6{`bjMV2#sHRlJa zJUl!Ik^!f~1}SmYtOU-)Eoy2Cfqs%M5C zF%3r*lbhnR_slop^|2Ve{;@uPmZeuo)SQ~sC9}6mCizMgcY@G9GFW2IBX#C;>&(U& zXE~qXF%6vVtF=rwx!DJaeNkMNyMH-|NzHuC1jaw!t zqrXzwYdz;3=Do5$<#{q#n)CZ3Twy#Y8U!;jE1wtn=cRH5@5bG4=uypL+{ycN#&?H8 zPC2U_agPVWWue>gZl=m2(SOps`V-#nJhNwg#05&3dZoh+EdUMyj3ggCvNzEPTe-KZ z{;<=a&_()nc(@E+wmI-{e_wI{eWo4$qOp#nVf5dh?tDcy-Ym5h)*}74#|W#&!aO+{ zrW|~l6AASrp}VaZOdkld#Z|<{D3WoSKg`d*>deC63JNurTs}pQC^^DqZnk^07F?Ke zdFM03{Ca##v7rQ`z(rL_c6H~X6{@i)?439!+{eehPvU-xYQ%W9Aadj=#Z&PVjh&yq zEs^c4d=%qWkB$nDd>A3?N=(b_Hffu5+3W@zjz`==7qg~dXerax@9QZnDrlV#xrcoP zwgo5FeVHCZw{6IzTDBDY^09^A{%*OL?aunuGRcyn6fPh3?W|Y^`C0e ze-=5qWm4pt2F;{RkU=_BL7$%Z9&`mcIma$H2Cx4QMeF+Y>qz&pu|KAyq_nMXZEeBF z@Zn8dVeIYEg5)-r%k#4tkgp^S3=CGuC{sKArhByTz1o zbl8?E_3RP-iQxkdQvWZ9k|8Lx{#S5jNY_djXA{}cUn&0>+e{75*_gEZ&c=|WeaJ(s zj@7bQjYdwWxa4T@7m-S5#?eBJ&#)yfZ}QkB_SXA%=$K;~f(S)Qc)}Wzk^~AYq>$1F ztxa6BtY~CsyhVFq88=I`VlLB^#j|MPQ1tO)Dy@(-@BY^|TOiE3xgpwg_NoQ4ui$2V z@87k5kB`0O$A_i@J9n0lRcUrIrc{~{_q3-^ES{6AlSt_OBIBRKEK`lXOKX1N7%=||}tw&@_!mZc?u3IO;>JC%R7Vm*}{eIdmN+XTtuuP6B zbo@PwH@ zVqlyBPAPWwfqz?%%)Cn3?KiMqqgZ}4=fnV8VSI=GLQkUcEalMFCI`n;zL6Oc z42Tz)$KuZFMr#o5x>!iZBHaTc^DIt>zE|D3o>$vxru z1c7-ii7MuS?B1D&tJz|Is#sZ{AlSbId$bU8fTE&eicWG*)kN^W9e zVsJR!Dj7f0-~azmoJf#>NV@1*DWPHiG^xOZz9~P+3xpwVEGspgPEf; zgG%Ir;c=eHASg&P?%1)=_TUcu`H;7$7I~%-sE)WOD&OT@qS`&o@vj4*LtSw!kQR_d=So)^cV;vg8$MOaJDn87HfvVrDDja58U&k(9?hqa2le z?&Xurd}!hX`cm&_VwW58SFNwp`_!cbSifnB=gVqXlGpGx+nzz_N~Ig57Q_ha(4MGy@=+fULJ_etpksdu46N-A>(Kj)C@p=Wosn77!Rbg^l4_EPDKENd z5l3>k-ba;&APK$ejzRdBvJdjUKd<4;*fi0YkaoA&_v^BwqGiJ@2)AtO>}+hyFyR(c z;}v3wEW3_!W8&sIGV&*O(LjL&ryH(1}tM<@ZCn1XxBqLA#zA=Vi5`b#8gTSJakVqp&i~^H2 z5S6qA<3EE&)t@4u*`ELrJ1cKMY_`1EqfuvqOV0z@G^s_{z;ulaTj!6AlH}6bI)YW1!6q~`rvGPiSW?B5Tpo+3=OqE9 zu(7c*^ezZV;zRkQoK7)p)UYAb`~$l_Q-n{j81+8n;rWWkq==AYhD2Oa}H&yR669C--#(rvCIgn<(gF!jFwH5IG z{WU;rK4fC*(<_I0A#DEe7fP;cXm}6Bt*n}wo9sl*s%wf5_owlCC)%B;7n;|E1@qp9 zf7;LJFDiO!GKZ?FS^2vRBAkXAApuKh&jq|%Z>TXu4GMoeoSkdX8M(66AdPzSV`(CG`wnZK4kzPJMf zIj}~3uwNhkxwfXl#mmebf*5-uR-)Y^c6w8}T@#I9lEFcC4riJ%f}sX{fREp981F8m zrS&k7_W(Dq`T*Z_Bv&wNNP+9-pGBsh##>*Z-h1p=bPS+X(~m6L_1EF2?-IDj3;rnx zbz)*+MM_vsS8+mKWC5nINQ692U)apYAq1(+C7q{H-P+zh2VA?*Y5KqSpE3b_l!Kc) zoG*+)UFD}6WVsgs$cW~Z2F*a_iaX(dp)huCQVNNbCuuK&|;ZKwqn3x_gGBP3oFSULDb>+#~8c*n7OI>9M ze-?BaEUv7Gz!gO@b!=i{errpE%N?j85|K}Du(Pwr#Kc5! zSd+qm5+UJ$#IxH<2581$91W+pkhu+lm4e`Ti+rN}!b?8W^sjJgy4O~5P@ZD0n$KTx zUPzuGIL6cNhg1C{^mKG!nj=BPRNH$31iSgXOqL}7(A)9Y3jL#h({*QgK=H#Hd|BD+k6Qpr1*g@h3iT!VB zX||vy0*I`OXqa9m3zdhTBJNhaSi?~Ar@`yA4xT@|!^*0W_9p#n?9&Ku21qyONfK{q zG+nP<>8OkC9>N#cUPfQx<+##wv-$MwrFy<@2R_M*izm}7z3nPJ>0{xmecU%-$R~VQ zneXr%~pyi67xE%!?aVlvd={&EKedDS$6hC;KtY3B`f|M zRvEPr9xZfzRP)KN?2fXOUY8oXOBnr0Gumyk+V?i`*oXJE-@n#OZx-0O@W;P{)lxBP z_I|G4I3FZN(M;56+^WsV>}ey~S|C^bxss7`{sz-U%1?MdFi);uP}QNj?@fm{Q6Em$ zuV1uUy_GoD8F>_p4ew?YhL`8!rSzJ|w6--~e)eW|vJ#^!m8zimysr`$`K7g0asGHI znX9Tc;qBZ+Wtic6^wk3=O1>^+|M-IYs3eTJEurE|1oY)Sy_hcdB%20WoRa(hVbG@$ z&>3qus^k@~kpeGctlX9gVZQ_m3j*5k4>lidH)`nOK>kQ^cDMrBox<4OM; z@oH@1cd73TXKPM>0;_qt+^<)cSNs3fRnbyGd$dp~HcN4Zu+cr3kB{E6ReyfiHg$#(iZgv)b= z-1@0xsgkosk3xm%s9Ic}cn?vqB_Hl(y!;S#sDO%OUb(P){*fz&Ke4X9|Hm)o9lB$l zcQU+J#rSoH=>O0B>C%kh+!Ek&1VO-m2?_fZkfprxOiNU7#e^vbaPBR5h&4%fW>W^icH!a=EuAB=u4rJR0koxphJ?N6u zjhg2mf04hck~&(pr`Xlm{mj*%*YqH?e{m8&v}qpii)AoUIV;UV zqOszUjTnYqlU8DHUU`mCODC&LcGS;?S<%qi2WhXD?i%atx-~6)G~>6$t}Q)=Eqq#G z5onui=VsQu3_$~zgALJFukOPx)KsZh zE?9?)@&+steXuP8xWNdq58w((-@kviQy&`}Lzs|ZD-FP1TiQcuS7E#bugfj1rDAD( z`@>>v&{7TQSqQdsaRrq(*$8L;ARB`5{$D}K2Vg){QYPT=_>p24NBaODT{j0zw(9gu z#)SUy$>4?~(;KxG-g4!+0m8Z*jcz9}LZpZ?uir0TK=wZ5us-X_l-|mE=ia8@2=b)d=L<+({*(2T_uPH-l?p&) zzo1hY0LudcZW}v17l)u|gS@I1mUoWb7fxdMTH>$#v@aeJRc`9L556Ew>~v>yH>4ez z_L5~LA7c$nLjl51T$bY+X@`40eld9dvDI-A;-#H<<1uqdms`%`)$?=IodsI^0_Lxj zai6Tn@o>tkhJ%5p`h;iTR>|D1 zvwn{O6x!*z^OXy_$7(`Y-?D>B6{*WGuHU( z6>oUOJ&6EW@}-Jtm1cTh{e#(5Oe_Q+6o}HWRqM%qo52#A7j3v1?qxndzA(|@L7U$A zM4yCbrgE2bz)Q|xT*UUWd*^ua$Wr#qn z_RiUkE)ndMgdl#joWI(dk*K)B0eau}8xQQ<9>%V|R}Bh&<&fM6hIS_%qpP~arowij zSkz#Y$>G+6R{iC0r=?Af{IrKeUHGb#=S_IGpZKh1R+))I(#faNtfL$Q&CUAkvASzY z!S*S4*+BjNS>d4fX>;>HX4nTQT9TD(+HCBjvF;P; zj9a8W5$;O;c}0nP1^28@kS_ZxC%xq`<-L)LrtB#^4X&W%F}8j^k!#*=pFJV6%707u+*GAXA?X0%F@U@72ucuocg|j^m8#e zMKsF|VvZsKIdMfzKV_3)`0DkIgMj6L3sQWE=4o_GHKV~*gyP_YuS*{b(lb;F4%e;w zejEg_4LP6<8r4zUbm;JOlX3Ubl#MFze3u zVyAN!jtB-tBrNRBs}7^}{Ie;JoUat-^D*=fj`%GcS<0+*C_!m1j!0rN~`J){Wa>;JY{*Tv;({TD)-h`ETKdB>4+m zd)%(LH`#t0*>(_f3AaaKW6D=X(RyP3OzpGHrUUZspk7*dyhiMQM;6&Un%D4WiV(8s zjU`T30w(S_vRckyLR0_P_W`G;hP|bxXtr^(xiqR2-~45~AQdJAOIQtuGUX*=ID()p zhxmyyV3lAE!}A=4`IVK{eC>t^K6frKu7V(&uT^(-(4?eokv*lFyT@C5VE(oW`g?Jr zd89yocLndRtSXDD{1;~vi+iPBXYz@w$5)i73~XZjA*FY__MNuFXTmG3)u z$CWdd(rx-2)Xg=6!E-714m;kg47K}5+=--r1%2JB&|%#ZW;1O3ZS;=+Zi`eh8AE#* zB>t@R;t@7)uO9|5{hH2ad6^yEL10fXI(JQDGrpEW?1a+Uip@)3vj! z92cmrt#a2NH1d9Sy(k`*7haDm*_y*X%vD`acMZ(MTAx-roVKUkl7IeO@VdTb>-qWH zZ?COO$m?wQdP0_i7M7+%v~6sr_i9FbpVNQFxY(Vcdbs`iyWCyoQl8$kDcdtyBs7as z!{LM~xeKnCN4CVK7MIp-WJtrE4mz6~hlfY*ewHo#ORXD|8~F1=zdOF(Af_!wO%7f0Pv|ZmYcoH0a|~pmEJ_PN(WS^{h(87l;%JG5F{fO zfRBeK3c$3TgM;Sr@hC)t4YXF1q0A;gCGpdQ0m>awLu&UDl7$}BnDIrboM!EL&|D)z zb@T}CJkorfbMcFfD^*Hl(DAlq&4*5uA>YVtVq(ENt!o}z z&|&(`Ll|=}=3QdOK~zJ?{QUQ#U&1*&H_d@?eiPOKKZ`2)7(l`wx8;Di2H`NMIW2pD zKNXf|#4c@venlw}@eI6G%rtTc-%S-%7LlDpS&HSZhYVnAB!{ICV2!-m`%M&sR~U4$ zIetMGzkUiI8A=wYDnMxQ_VKv`7}R^ z!~c3Baq{oKHIF&gzaCT$`i-0NU!b^ue%@~_kKOR<)l_m3Bd#U0XKHoGn?Z(LFB+LR~wuxoyLA34;oZk!=f!~XM}>%hozjKg_oD&0xfiod-tv*6M0{MU2A@O%q+Ovorz%2({3>`K2iZ%>~%c(b+5VC z55qoiT(i(@YtG}Z+-)3DEAlV!iP}m&KhFFq?k9=K5MQkQbF}J%7p`GsM9uLQ-b^WK zBafXmPNor1FJZT$ByRuj6HKL3t;vA2YUSsCC+>&kO z{kS0|>Ua5w(eQA>Xwzv;ZZ%!Rr#etwvgmk#%2_w>5hc$<%8GZb(`PBC>>9GhCVB7Q_r z+$%ZfcM&2uA}iB;NQw>|nXvfqYU@S~aV`c@_F z$zauVJ03JGgT&^;Fgz4byS}y^GuG#ka^4?1 zKf96}TQY1`G}nsi8x}B^D_u(WV8BavY~bvCVzSEZRQ;i#xM1)U)7zNx`Cn!VA4gZd z1~w>@A%ifjEGCcEu$-;_v1N}TJV1H9xPI1g4EZomb4PIV6;fekv+eOAA&#s^P z!4z!9$8r=`-(=3*vNnjt2y`#}d9hFXkiz*S)ApggEC0}BPreV)*oTx16-nhUoj~`T?lC4zm4*VI~24TA-dLaM8sykf^3#o&RF@(<;@<>sqIq(!%HLh)7 zAk>#62)w3(ZemLVeZB0|S8cetF@^nVX^&}g;|i0U%5iyx!s@A|uZ|Ig^f%&Q7`LjE zi2H_q_UPed4)Br}lc#)2w}?{Hi^GH){aB6nd?dUTL(}$MT-2**Ew#zLxSP>&9D8w4YV#}YD-@koZ zuPFI~spOUIa&Ssb!-GrMValfkQz8W05vJR=0E+|~v;-7c8S0g#l+;|ndjQEE47=Vi zORxe3x$FEAV%vz!+`;Aq6AKIZlP6!`qo?jCb})w%($gb{y<{(BUcX+4@dtuGfX$#L zg18;I?9+f(wE?K;py{L#=z@)4XU9|CmX!3um1Jf3pbZ!Qxsug*nVHe22e~))Rokw@ z)fKP%)HPm0DL-h5&HQx+rb~cxXU^v_CpZ3-<@WAJZ$CI;^#vKn7vcBtcOw^+W8Qd&eW-m($uRtd3>pFPK?#7*DKSl_jja@|qB9~tAty{FbCw7x0$&G}hNu2nm9|!G6K|#VwnMV4?n+yz7Mj1P8Ic^NZtD}xQ-eP? z!Nbt9f*vC1pK`{YrXsNg+`-Jj4oH$(?av+G;tW--Mf$Oi!oL+?@N?2Y82_GUb{V)_ zrHP~ZPuJ^}lqmM}8>~Kd?im{Gy^G}IM7IoST)8F|Mi;rXtyXRW_GFZ;$@2H$eW#?p z`dFii19nxzEn7GQ7f`Im!K80qr-;c^I+(+ok^#yf{L!Vra0blNi0#%uvp@hxVYC%> zN=`wct-H5HoB;6Br!bl9nt}C)#&ai(pPckXY|ux!$WzLv8HCXj>rOlgYLTTfFvpfe z7KT38W(t*}iSktGU*uNmf11W1mVx_>z&Iw^!m%c=Sz;Y!LS;kZtl~x zku6r?80M7CG$}_;-K4gm!xdkVm7U^y$SW?!GCP+1wdHIX6~*^!K%()8*3!M6#`vaw z-LDL*OeaXX^Ti~?ptP2p%zKKdsH76jzvf~$ZFZa}bInTj zoJ%_4>3yZ-`)t;RNl(-j+cCbz{Az{w=Yz{Eg7#kyf_Gek4?eHdNur=*$bHQ{8R^Xw zzfdByrLtNUYi8#(oQ{|_&`S9B8>jjaX=lWW2$`5Xas!(y>2iR+TZ5ZH@O{%aYnC%e zH$VEOB7coZC*|xz3Vj>g%|?CMy@em>ugmki#yI3sOOts+t+4xvii;f06SiXs=J#|` zm;5FCvQ55NWDg&{fu&NC_DgUn`{3mzQ+0IejRw>`;NPY|%K$@iY&hQ>Hb(0bp1%hm zN;4qNU?#UZr;Vg#5aee&U3+2|qc-2B$@8)G3E8{&NG<*75ASWSj>W!qd8UT)&284} zCV^@7?yuC%+6ArFNu({!qS(b3gI-=BV~CpVBZ**ya;1yJfW z@no~@pitv&bhWpLJ6UA|>WfG-=ZvPiq*U&m1;z*BdJ&K6q?tX~)^Y4LtgRAJ9J+U? z1&qt+I7>;{Lsiox9x|1QrD`o&IY_mA_K9S4D4##xt3t&o$Cwr#DO#|-I1G(zl&=iV8!XDD{ONgih+{d@8W+3RtX|r$} zPJar+?wA;U&p065_+ruC{PE!q#>z+@2^$+5U=ZSuj+_wl8zUp5sGo&?a(^1)vyuRb zo*n7|i+lgt5nrrf9sSc0n;GUbevO0jNjro$GC&|+clrPE_1^JZ_wU=d_R>P4B`d44 zg~U}xw$MN#dzYC_Lu8a}-d5QXk|YgOc1EZ)MA;)-_V^voy1t*^_wl*!-|vt6dtaaH zD&Ftc>-jv-^El4qJkGm5BZnO13f`p`++49dEZxxDQ+_8}JEMO&U+T-lup%e^-N|2f zvhnL3z4=9MuZEkrsrAd)o;hvlaXa(#HGJ}3%}SH6<|{F z)Q?i)uIjS3^tH;B+Fj8cZ-ZMbuQR!ub{kAYFUZ_XIXJ5Id%pL>2-CeUY45JPLm_`bLrYY^3qQ3_a9qpofsY*&BtoLGcc{;`FYW27U_m5gLqGfYleLu z-oG3UY^Sxj)xK9y&NDHQha-RZ*UN?&MRm#MaMg89=VzZo&w|cEM|bzlk`gI2Y`UvL zSQ!`?PL+6h(jU~inru`<5k~f3|&q(&9c71z#O|(Z4BrC-XEc)B+m1olSgkGi>l%ddbpvo^^q8MSTbFl)M`bzgii5?R3VDYnd?=vtZ>I zVa}~vbI$j%C-8F1Ha>9XyV+_~H5^_x!!&MxrR27rVRbEks^teUpU78w7e^2kY#iu= z>+6m&Exx>R+44Kb`e3G2U-DSiDOFmGEbiTHQuQgu_1Uxbgj?H;#=W+y_>FndaqeAH zTJAZuN3XLidH0uF8wE|ry_m)$Z>i=7`-tusJkZ_QIwB^o%y+Nr+vB?_8(_qjOZkt}-!}SM;TQKcyM*_%wTMFPlvn9*sfP^TC8Z2_Z&$_hCS=$Su{~mX zONfF)f?KQ~nYHEyPtsS$3K%I<=?ia3oquL_km2W>?>zKEgY>mszl&Www0%aSD%=9I zY%>{(ZI)@;zkOZ)ndf1CJfXGlUQ6q`&teB`P5oABmhirwWIdPH5b=+05VI_|oJLWj z(phSr=wZoEs#Sgs>h5!gUisZTL!)OjE|~7FUNQ14gqfeB&DQB$dHqK0UWWO1iT#%x z#-44?_v>n2h=(Gp;hnc~Js2p3pvl_TufcBFE@@2(dFLj?MqU0UnQq=Mzp(ryrBYt% zN{*fBJNt8WB5I3I<~L0>@$Wvo*Zth}`|m$=uG!sl)NbnDA*$weT_(*R2N!bn7&yEN zy(kau=qUb0t>fxv7{N+q&d+(3$4~QtOg1)*n*?5@y52rke8-=!Yv#boxr5Kt{2%#+ ztkP*pi<+9QcK}Ch+H5|+h-WIhFH@9ec_eeCi=%&jQ*~XVoI;*CR#<8M5lAl^I66)#pZlBZoK9$ zG_%z0H^MntU!|pTKa}61ttB9-V}Oe%AS$r&yl#SKg6+>+!sps=DV+}uJChN1h9NfX z0##+1a@}GeQ&iR5_bNI2q!s$7H#O__>heYYD(ak>csv~XGc#D`pm>rP$?f9)ewTzq5*v$M%248&hZ2D>3gKS;xJ5;{PHmKzN1%y{I)XL|N6{N zR>?+1?bOrL8~NTF&2I#S*cvPhPlim;1KUf1etP4-p(2L@HKb=ebDaK;>3oFL%wh$j z1jj;kie&kyxB2nIEuvIkUFY(>1F`)r@<+qBFVO=|v}T2$)g)Er9(jM~*hU{Z)uQzW zT3?vgU$lL!&Ea61f9b)Qkx(ABm79Tby_amtWDzA-n(`8(!W9>(=tckh<>((z=(%$A=uz+rx9;C(#@dB$EJGl*23#zM;^(cg zD&@~m4LmY1xq55OCi+J%V;zo#iQ-P&v07|- zKj1X*(m9OQ?`eAYI8$4-TtBzL2b=9aEx%qa4?J7m@w?c)yxi#1%Z*K!`*lsIw&uj< zTT%q6wqDl0TPVM${mS~Eqx6dhY&s@7e#HHg>#xT6<>}S>xhX2QI?qyG>5U!Q_gAj< z-RN3!tHWF6`q+#6CCmeAPKGV|LmPsJwSPEQ?#XRF!l}(plPDN-dHuN*_8rOInWr-~ zKIB~3js3+s1(xOTCfcxh^T$@bB$*A=o0ly;>LPe{^6I^G8IjC7ojLxgeI$$F_8zg& z(NWtvc67zVm`-XWt+=+-v*60JTQ7g2!@VW+z~00$Zqe>@l;yWij>#@b`NKE}_^R<%0H!@{plcf5jT^0bu7tG^IcCdM*^GI;PY zyXF%|A?L$`UcUO@MR+%C;_q14zPL>D(zB7KWu*n}r`Fj{*Rj)-e*|Bo$gJ9@TPQz) z-8*!O=K?#XOunnNOpDpbPV30_ote&kcZ|v5&hVq;bKhAq3PgE!XqayKDt3TouW8lo zu&3c!^LB4v&$cG>37vHq49f0#Znm|~b@oHh^=`>mb^BSnY!yqt9`--S+qL|&_aEOT z0j%yw0vbJ?trLMoOdUNv*l>JwX>1Ac<0M27%?lUOlw*R{3txy|cdVmH;i%qfilIS_ z@@?PO;SU+=&4X#K2H5a8G#BSec{v|)b*T&$uhaVxDivA17+`sbBtBbmj&?`C2B6PvT9I5sLRO#h%;KW*984z1(b9 z$lFjI7e76lb9ozw^B0X2N9y(`?$xaZbLY=h*RnA7dTgMS#Ou;l>9a&u@kw7#^wMpY zKYMG##d%&a27x12=UWawa~3vvUL13ia$~oX6!os%HdUSOJr+5Ef&BXgCWi(En|^mb z<=oiCy-n#otKcWKdZnC|d8aSOYghzt6lUp);W9YRm8<#VZMc^8UYbXBF}H3y2?&2( zop;4h@1RZCqpHZVfxKC+(}!84O;cXaOD0nLQwt_7UNwtrGdpSih`*?{V~l~ZH2-9p zu4IhZry51}O%iFaZ}9Gi-yt|UAFO8y6*N<=Pn1%_a!1exo!E=BY@T@jsr7we&(m3F zZv%DO{d}_qHuW*DLzc@yQb>Ch2Yc54i{oD79q2Byn!FYm`B=m+qTcM8!h2RkVWzFX z_`_EA_0;d%{EU8T@YjAG|7XIvVN7j>=(8^g+Be1@yXLW?@|s)zr6w|HeCa}MMaI+` zr>~nyk%mHA((;>*ksbPbuy`K5yrhL48qg znuU#>;m6V$h6@LzJmxPhpZXcvsNC+THsKtc$5nak3H#Aaa^39ujSK@%*1v8Nk2!a| zLRZq{?d5#?u;~3agc4UpBzdIq@R`s!54RfpD7^;q?x*sV^E9r!d91A9?0z(CNAP-}BA` z=8Gy~UL5R3e!|Q7T}B-fsZHMO6Ci_=3A+?H1|Dwy;a#WPT+>Z!NPM3?=O%xm z_8>X6tW0L$Q?`<$;}g?ZY_xxD)pGc$^_MqjR=Z67VuYVaOKU=0Ty0^ym(qz7E4>%S z*1@2o0!xh$z`VXruyBMdjwl>Eeo>|KEJLP1gLcuGikQn?XZMC}P_vF@G#k{xhC_cjaVKcD;C0taHrY`lC24pFmTGf^k@fsDn$Zlp8e}a;}XD!yMPC zS8h&tdv>Ik5^P6B6(W!WxN{j~x3oe77>G;$|N> zz~rpq^gkWsB=hAHiY!w-?2?j8H}1nkV-*}&ww7W*M?qOR1!NSEDE%SD1PNDB_o;(a zaIGl+{{2E2-3sFGh+~UgUB4UE0{`~Z-|xbJ8e|7TQD`p}JG&R?)L}hahE4&uzQ@=a zs)j_V%CfT6=g)r=`X(+eKE5#PP$zQvfNW-AdfQZKH30-v9#p5xJ9w|aF7qoSa& zu;<9)++_b-JZelrJej)gzV%-U!RldlcC&6<6oadq+hh0XOUMvJC2H5JOMUo2D@#dB_p zk&zKZrb$J^ZLi#C=I1q26?afQIGyeq^QUAfxqK0kRotqJb6}Dmj25fAc6|AR@S=T*t?rVW;Mv*->Oxs z$fPFvOlWW!;Zsp;HgDei<(2ypvL8(`0<66btnN4xy5h>r<5lTQQiRmZ>w%et6bM;ntBKQ#*LP;)g3VrEpS;#>*O=%2*Y{gUde4 z{A^MUC3+jeH0}}$GKf8S3!+aLwqXRrgyWm!3br~Wb|lw&-d%XEhl|;J$7-t zRL}JIxCzzA;tk0yDe2MYz0&s9EE@=fPldqc=QVD~58q9m-&`O;%lAQL)LHVYw=`^XbEc z{x?kPezg_-1>iYJTaye!k_KgKgNcrLDEm;1FiCcKrTY++?vQ z6a03={kkcM;>*6^wM;ix-AGnqxv5yZ`0ngEooTP*Rf4ppn`_=4V^X@lQn|>!iBek0 zR6>(2f|n-f@zbbhivzoW^0LA%|bvN-_t*swVH~+#=oI$5Dl9*s?n0|;i@m;Bk zDXV|u$-dSiL81kNS1YCk(YgU>#y_B+a}u;NpRjN@TGzzy9?n;3Mawu-O%HoA&t}Cy zCkS9z_TfXggzGq;>v)%Aa6B>=wj}<8cK_J)bW2CFN6CM~`GLb5o;*?%J8P^}v+h=& z|1LUt<(a{u*yxK_lYD8qS)J&kLh>jl*o~gq*C;x~CuKZys|o1nHgu$~oY&GxKOHbR zTdx2AK}BSk{D*XKS)Ak&EKU^Yv`Qb0{!2eZN2l!_7ZBET7(5{Y2jA#6-mQn+U+upf z@~m*mt~Zn&Y9mhFfm|j|lae4A6DsFi9m_*gTh+O~mU!G@JF~bR1{0kyoAMYd-$_X= zhp+pZ(p%eEqs1H!pm9=JKm2`1)DZ$5k>9}B?0Ik|i%cS7*wNGK1zIMUjC_Y&APOU0 zSQz&Y^GZr4;9vh~p(f64YaeXdu)F?OVW;a=F4WWg62CS`WfwP;nwFo+I>YGputXEB z`yjWnY^AdjUU!?MY+EV=o@q&YG0ZXKYPRJ5qJ@M{}uYChBz8tfGhNq^63y*E^J*rqc6 zU8HEQit7at-Wvb=_fKdB-*ucGQ%ManzH6rokUgn8p#?J z6UGCng#2sE{Ap+5Qzzx79}*H$8+#-eHnb$IP;I2+{HMV3W0N(U?8-?ggiHjy_O_y; zCw?9Vs(;9c4}QNJRe#N8=`QpotnqTL9TWGw5qgGYOw1^|pmXIUZOxovy9^;UR77uMpisC)Du6MPYibqY=(>3xzQAxA&#!p*R_4zlSAC3Nk2=DoYmyho> zXWu^Q+iCYDo?UuU?!XC6`pCwfbVN(?V8E$Pq0pwIaIz2lS;Ru&dpr;mD??GsdjZ}fKk{6(Msu`HuSRG<6P zMicXIG(Hk)-=u82pB$3zbLb z9*#)1XchDEomI4WMMFubo$;!%&fVL`aiI6*hT7I84m(+umUz9)3_Ei$@kh|K{W`A~w!7W^*xu-+d2S91)A+jTmxEWrtITB+@>n7x zEh_ysQ&YEzGwK<3=nE=JhIggRVPU4$iz|mvBBq|r)*1Q!>B9#)bn4kxi^b7AdaBg% zaZ~5k%L~Drle>B=my5m1N3XE2cN-sOl-_=yi$DCqo;x;EGWB~Kzvq7b%RAgtE|9Mu zR?Fbm2$6C3q7o z2Nx&2B-69|^mv9eXm6O!(~iCmstdFqVCTACJNx%(962DkNf?lm9;`9Z(Rbq(esVP+X0*O^6|8f@#4*F}^o8_8r!%(o^z;yTjeVuX4pOMdIxuj3 z4;w`>qwJSkJU7sO?CLZ`QJ;b$R*4o>gq65ZhZy*Ro@n$c6;vI`XBGM!t$S(AC5ZaR z7go)~i5}CVZ6%Fn*O`QO-Q>$N+isY=IqzLa(-FG87V;-N6lup=4(V+heIJKgM0bc* zp`kJOa~}6OO2HjRga1uMe7tV@{W^dCDF@qRFJDH9bcs~c{8JUq)hDgPS6tb`rQqtA z!o0z5j#1=mu>^<1mA2j&#mD1XO_V~K_&u73*&Y1)&Fb!bHh){_meXNKeT&+2-tEFW z>yh-@sjvM!X-bvZr|4`CZEMh!qCKlzbKB~*=)hA~{}4Mx@6WM8L8XVyLeq{MRJ-p| z(-MSrD(B{w7JRy7b_B}x_GBF}Fm{Hl_)prai9Nzg<`v+9j)|hp1>%dRpW$p_*7pW{ z&~I~}dGP4Ukj|yHmkLl`QSk{18qJLUq~0w;O-oDr;B2-c;11?#0F+qkib>&ZZ!Z8) zWZYitdHFZ9N%$M~62;~2# z&I-80XZ-PluFvXSMkcY!A1}WF6S6H?%|)BEK9bZA2bo{^C%@DPrGw?6o?sS8Q#H7} znWne*Klfgij2Cz6z#L~;MFm+n^4zii1U4%}VPx@iFZ5Ly)*_2^n7n4L0r6rx^6RnA z%4^~Mb3|e_JKinfJ{1I-qA}l0P43Q~nBkfhY(h6(m>B~zkhr`!;>{E!%)+vA_wL=6 zy9(dPrhH_BQ@y8oK=4&VPS$BPfzHazmsgm&OPjOMv%P&wUiivQ&kb9* zR(=&Xau?GqVYNKH=VnOA6#Wqu#emM4o7I0f2>(X!yKHhyV5)-I^mCXv1ij*Ftfti; z8ylWJzRtg~yn&ZLwCDkWVB2y{iW5i4KfM=^NV?Z#7@-+E|LMOK*E~dV{qKUD|8#0u z*1Yc-_>gG!TK?ZAaOVFstp#`v{cklje!9%rlzZLU7GJ*=h>*^8xLaft8@qZ#NJ^^4 zlP}%V4H<%89Kv0zE!ZU$)AoqpZ5cL_kul9_NWYa4?$Y(}!gCIMqf?L%Ql*E!{Jp!X zU17`kY-mGILlmA(dCsF^R(XB=SD?qQUy9I#M;mVGMqGUShV|=9Yic%rED^nCEF-fT zb3O2MGN#Z{DJnCaG@KKqX|4>3M$4ljg>xekGz<^SPC0fMk&kG6@#59MKqcRyhOb}6 zn>|KTLZc<`lug>Pr3JI{d&UI?C|E@#owj^(w24wA$00?j{R?RcfkVFU|8&PY;vt73 z%D%L;G>Gh^|MN@9&q5=!qdAijq>s{)!IX)5MH&`D{yM!e6Soc;r$m)y%ox z%y;ts{#<4wa9H`|z%~*|k@5BQ9T479AU?!cCn#+nyDMxPqiXhzcV<}h8uC-%ZIplU z9#Pw?xC;|-V;ML~2WI09NE<#85mQVk5J5&t3Y({2#Ni0Va&QWme&&I7oLk`A(*516 zV+h)mXOoLws<->$Jpq>JWNx0Z>4;nWK&=|h_U*?JxUhd{ zGeP>u7KBPL4lnw;Q8RHKKZ-cjVW8_4wsY5ay5w_rc6Lgm2Ghb~qkAP?eRa{QiITU| z(>b7ZCBaiXm_6Tp!l4&Mu*K5yfMC(>;9#|h>F+O`Ej~YDMr-B0l7x4Zo8mSbJ;{?X zgPIy1pXg*87oL;gfE@*7<@@K)TJUU>FY#LB6B7F15N^R0a2PqCfLXlv?xC@9j%^uni|aH$~7DN*dn(ocad*TYPf+7y0)MV73}Tp)8-}UxDXoz zln4Ck;rOc!pBnHm1bvZKFc!KyEH8N;J2?~eLBA8UE&kijpFdxtX;%cfD@M3};!h^- zxoo*r4VM^C0viR0NK?f6^WC3gCBaFY47+w|pzmd9Xjp{_AiU}>6rl`^j3&?ZlF<+q zfYlD6=&h{}u3fuUeDP-DT=CvxZbC%x4XWp$)}yNin3NcSMONlLG3p$T_?!FD_Iy1{1m)s zdS)m}--|fx5cfn#P7N+zEQR1Kn$O_+0o4l+K<>5V>Q};=2421^w(Z+@2eUf(Vlk{- zit!O?b$@T({f>@~XSP3Al5Og63W^hRSbO>MWqMvcW$cv{x?MVFKRa%+zk8>tWl0^r zWrlYC0r0tmwmp7hZDaQNBOouglp^a$TDIecTela-^Oh`x0-J&Q4MUtcDMj@!Z2$ybhmT>>_pcVbcxjH0?ljKnBu9=%2Q3I=&p_Ru1{XH=< zhAR0c#9YP!U41x)lfS-%;qTdXlx@Ipe+}MG!LIWI^G6Ca9I?6=izZ@(ENHM#jC8x9 z5{SYF8poodeCH9p?DFx$cPdmclA5wJ+VTSxCV0v3L z(up|~X57ga8XFtK*dRQ6m|m4V#m_>ZtHh03AtbE`W%aY?&k5_gG+nYx-Zu6mtxgfr z1Wb;|$jI0_EF~lqj&H!{GJ4T#Y1Rzm+`;J2Bd&D7#JS0>yRRTs-y5Z+rE#4xi*Vj?jyc}#Ar{_`PxfnqBVLn2ZGgeHTi9~)7y=3v zhX*-^f)L{(Hu?DYnCCdy*%5amXq+2MyuIt@<#sB>DyF^x0M*pgtaAvVRBhcOdUx&S zU5{KROwl1vpH4_dU^F7adewdBvG9>ae~O(p#b^dltI}^ zSvUehfDU*bK4j9*zFRR{;^~Jaf3mgoyK}pGrUpB#PCtY4h4VGhPQXhd5bg2eg>fZf zGJ&YgdFDa5>bxnaBRsbhL~(r_gVcOT3JTRL^V;@L0-Vam_Cv&}1ET+TmY3|K~wL|%FGPML8AxoH5a=Q!Xiuh-S`ez zZFEp2sqe>+e^7oFISoeE``*>m_k(a`d}hq3CY8fh37=^MPaSsPP0HSEf?NwY{M5UHySWA|djv|;=w6;oo z_e@t69KrnyW|B(7IL*xL?AUm>Qk@76e2@3?JQG4JT-xCY7x|OvI{pVt$>N~`(!_8c zZa#cE+4qV&UPRcTbP+pp(rtw!aE^XS{Z4(4ko$HXoE7+0mc9=#yYm+PEA3~t%y^Nj zFV<0nPe0TOA;$u@klH(;E$$T^9bHPyD`RVGWrU_@SB7@s1oxtwL4|BX!@xj{pfWX5 zH$uO}45TXE={B+41a{+@*P=L%;JS+t8^Cqs6e7ev373CRjaFAz1K5UbXO$z3C&Do@ zCN)0&P&qU>n5ED}T59MsWum14boF6!nu?rsysNa?yiqk&LCVU?TG-cFQBm=0xr#){a4zkh#9R-MiS zogT&eCvJvs+`-LxdzY{V_qm*h;qU~5^VcalS@qD+P)C}?;NV~l2zk4a$|-}x?IpR6 zLtoF}t34KQ9@fQA>4qAE?0KS7Qc_BVVo4Ff^+{CR9cAWwpH z^w`mXufaELwr1M7Gd)67(ikG)8qk{f%;6{`xlq-e!!6I`3`lZS-65;~+<7EtVYWAs z@rrJNPQ2+dPV*TInq-QKiE*(jMV|hYb0G_V_ThyWXSvjqd^8Y5Qx(DvD1u22M@-_v zub1|vR_8wZF#7(;_ajETBt4#yufl%v&Yl1as5BKhn8{|J}UAB$RSmMB4Fv`$o0!$we6BF~;ypg3F%`}Tk6JulQ_FYx5L-?qO^q*R9IQIe}am}fLu94gi zyh6%WQR1`nJXdM03Uyh|-`N7fU&s?^@ta zUbuY|LgVO_UqA3HfZKie!Rx-jpEg}?|aXTT(guLyx7ybC52ir0dXA(jo+k(4kov_;7K^t zgk>Y0e;C}7-YWV7*TOT$5s8+?Bc0Xtj@0HNA|aPFy>PxWw}N^=GAY!v5p@ImM6zbTNoX&ikZz90(uA@IzkZlm~yL@8v?d*g}SOPxc&%wcWq3lXvuU6f| zb;eGhIDi*y?8_9|M2m<>0SjY?@)(XDG1wW0j8Z>Zc?AZTNCnc!>;M<*umXk}1rnxw z;3i0hL65mjUPRps*yzw%u^Aod$t%x8$*4hp6T51HgaS$%%zE-86QPDC_L6~to08>j zzxn)GRN4^uOX$v>JCj4-c3#DkZhB-OjS};2PoNbxagmkTxFM$y_k`wM#=AD)Xqw_y z6aPUPcEyFkXG=@6?eMNA7XWSrDMiCLu0-Carltl3S7^^tad9!(l!8QHk4a0YX_uXp zN0K==Vs{bQ(*l6NkA-dM;@|T3HvlR>opI_Ki);Y->?oWOC61zuI)LcDJoowX(%t8< z5dfD3kc5%9EkI7@tuC8Ff0mXyV!k@8~C&+Y=zmD0b4nkn?@4XJ;0G3c`Nbn>W`%Es)Y! zrMv3;_jud~%#}_$4`)Gefn85@f`WqJO0I=(ti;Q8of&1u)Fa1%19JH&Gva4()I^_C zCa&PW#$bpHAO3<`kxIZte&9 z#3t7fhV&kYgC2?k7e?7-c+SGoJCHCtP(~947b0Z8P|gvll(vIDX-h8@Ff45tP!L`o$7=Lsy@{y})nEGp?pVL0gHSglT3Gg|~1x9ZDB4sWJD}(V!(WxP()H2y7-d?Ar(5g%2s_D6rs2vyF~U z2DDHS2BA@~tpuY2`*dlT-l49i%)@`Q`JuKTiCw5cm(D0NA*&;-tb$MnQ1Dc~sR|yM z%(azko?#5r=IayY!-uzkUP9>|VNiL@p$CP6^~Le7>eg58QK)S4&;Y>H6-uI2>o;yR zMD4ss(nBk34;=IOZGZd&fEK8eodzV1V*U=wXyZ`j_u`L} zJB2G^*2imJpmQ4{bMofV%nZVvB1{j~Sfwb0nSXl7i1%QCltJOmgdCsz}=egGQfV1t-lDMqBh6v1xY}H10ClnDq7kwq51qLPZnDE zU#ShabFs1ckPT;5J`RH)owqk>8F&VYa>@Q0+{CL^Y@M7;aB9e?BMzq~N?4E?DgDb2;A?=u*b8Ul6fgrA%e!|r%K|%9fEHR#s}=lg zN>yro?i2`-fZ*je377!X0xd$MvrU?=H0N#9RQ09|VdK;#_~^;tttHkJrT>vov_mkhhUJWVl=3M|>eH6zIJb za5=61Gt*l!SO6AL62X z8+OMyDLp9BPCq#9f4O+p7l{=2&vB}lLBfS^E0ZL#IRLIC1?*aChIKOf&k(6EWG>(6|3 zS8(@CpjuhIZk-_hH~8<2qM^F!sHcgA;Ox&n)Ot;<1pu%}Wdl(>DcO;jk+)FsxH1SB z%llH7o32&~4v9^lau3?a8@`WqtUZK6cbkF#Il1%?G28Xl?gkp8FX8L$jgucRQyKpzQEvjB>6;V+Up4n0=&j8n`g>$4OBG|olW zbE2H0+!p7mhUka3mr6Uqb^X+Ojvz< z0Fo}<)If8_>hnTf!(JPS%gB|@)UV-vML6NFg_nbKb9qrYF&{h_gwLD@)J6^;OezIb zG{Sw8J}q@Sq}*U%QD(;Jm#>X`PyJ=`?$xpzVIBqn5Xj zt@tUpy>j$g7{whk>`}RQBdON_M$(->f4&=&5aNNIfK`g<3Wei=aT1aqTm#sfb9lar ziU=OzAbPCyZh%ech5@@KA!~jYJj5(T7A7l%>z-?3e}^KxIsPDN{ATw-$*)?;eTXB9 zxO{YoOXZ(Fopt>^5b+pbm8g9!8k26?BSaPsCuc`X${HFbJ;vt6RM13({1CFTO|6*d zYh*P+%}|42D%j<6S#k=cI5$#y4PrXsDd0xV2?F>O==ui$xG6>LV7LpGiY830!3~~6 zIg|ox^fYZIE=ftf7=9z)4nRQ+I;rHReQO^{WHkT8U(C%_(Sgt z-RF0kG)ILggR=N)xc+nG@i*1g{%B;cKzo7MrGYN^{KAEY0dw8nEMwW>wSM04DdNw7CQ@cU` z7=mvgT5K@=q<4q#mC;(L7#$iIf=Omu7?B0y?v<} zPhdYac$WLf1|(CImX-?TXQPxY$0P=*O0rMWjmT!wh~lVlPb zyBpo4`+$!+OqVkCOC-@LNI%J(?Lv0F`i}IF5gO7A{7=Y^%V__u=#&oVV5UO4u@ z!DS}H1Zd=el#PITz7aMV*co1fk_Z!n?E1wX%CRE1F&EO$RtzrU5!fe?p{l1((*a^v zU=ab{AEYA+p!TTEOWs((NDE~Y8mV3N@v&e>M$vK3_gZu-US4uXrv#-bX&EDxYFpX8 z3`BDpB1i)25rQ?Jn5)+nZBCT(uE)nR$1oQsNB!}`UwXxVI_rv5`dys#wXs^V3!3?MpSmZX-yKjE<2#8?`> zJ!xwp$&XG{Udjn`}B7Hh?22;W-zMCrX-pK##v8YvI(LZ}N`bv_8%s zbRH;!me#a)nms8RbZf9voZLb%ow%CBBFfP44W1e!s(!)%)zzt(@z2iB(<0Ah9)9rA zl8il}bI~q-Oi^yr`t?81Lnh%J=YkADpa>`g`+jF-IW2(Y$|R4JI+J0Xm`4<)#p@ z-^8v0hlK210zuGx@cg}@6nS+z6{%X>6mXKqQ#BefhNBuM`ugWvKR}@O5=TH0u%e-c zfiw%@oRW8899vOiv2b$-AZIoM0b+bPWO%kxK*P|G1)tmq=bD(&5wQl6A_WOyVxmEc zth7di-h59XfSQ{6Q9(f}%Kt=J4K_(-n&g8A3ydW$wTjkR>?RC9W}>*j1CdT7LOF35 zpmb#*V|Yx|9dTQNd18W8P@fupsBeO6W65olUs_ZVrC z<}2olEPC4Hkd__#2gGg^7#$QxI@G|Rk)v>BEhKlN0tmi&^QK;?j;#7K$9@_z#)wR! zTkOHe%9WIR_fb3}LDO1>e@bXo1bnVX zHbkV2tea`5I;BHD*(3TKY6Y?w0250}Ln=}E_D-MV#nIqNrX z?nWavrnrSg@cq;_Bg~qed2sqZ3b>$M!U51xl9@4taim`&`k~`KeG7-4X4|$>d=e7= z@Ks4u6)OmNs1GRKba{Mp)9t$wNcI{L|s<;eu~Rz7_<=8$PNpYD^^Xau9{!Rz{oEq(Y*jtDsQR zLJY=x{TK&-sdjvP^o^hQv^svZe!nB}fRjxQu9($>^i1g!sJ;vV$6->}SnTPJ!9aBP z6MKvco>OFJn4jx19m048D!J!Zh7_@4iL|M}TD7!FVlsntMj=EU)83M3LBpCp{8cR| zVHpkms+VonztE{?!BHdX5v=XzCG&H**>$z?U?)$ZqYgF3M7?KU6O>;wFxcnRdbA%x zpLDPjoYqEuZ3ttWKi&MDO%pH5Y#pz$h3b)B8%{Sg?N@$ zJ`5%RGQT<`ccDTeuEBb!ALu3Fl;h|e_YzEhIPw%n9ZV7# z1A^Bg86Tol%r+$GWG@n3R`S6gb*ANnn?x;u5BO(m6TjhVjQBQ%`vVXW%^WAEyu+2t zp7M*Qyp|Tk(0{|#BGfe%>cks=MKna`gnk}gusP&}_$d1^+w2y2{#NZngfAC&cUpK9 zB2+iCoox4**i5cHc9(oQ|JKPA6r?1fZ{d%H{J)*l2?srRmST-L4{btJ+vts%TBvG1 z9ej@IlAE~SD6Ze4kOQnVG&j!>+x@CIO=uO-gQ27`GB+p7RWKWc=~Oj`c|135=nlYL zQ8d@DXO{d0v_>jN!ViEOt_$80B5dy4v`6BJR5<-h4c{i2p7-DtP{s&(C*m&Pq!7}* z?yEF17GP9ks?tuvK_UT>%#PqE;WA1^8o;@l;goa?t-eRf0Jm`xuagVfe_{>>u?xip z2~Hl|R~2Tr0gAx9D+*I2+PI5;tNkVJBeKYkqkia^3^LMUBhH~5NIt@Q$BaJ zz-Ow&KMH*-G;dtV%bTlQboS1+m_Hu@=@$Z5Oz{OCl*_VWcvbA-%f>&qwI)W81Jxej zDiO*O)eXQPQNscq{lM;DQ(SDc@asD4Gb55gQb2*4EVlVpPHeW3p`liRz4*11 zL2wm>LgCbX#z&wJ&@ts3-auM2!_Ar8j8pelqEO*LGY^{LTguYjo7qkbvaqr;;v9mk zSy-AMffmJ_61k3=;VO_DDqBhycDw};Ssb>$;2op>{V=;O4O?Nzm@TGGuvLwCuWF~{ zq4j|e2^O^s`6vUL7c9JOV&g6=*}o~$)Bw!xVYTcf^mUs&7MViZR+m{$OTn6ww$e+GX5bd@Co$Qzmy;zU}T?Wx5;n7)~eI$uC z9hBMv^UBz3xI$&3z;ox&5&aUK-(Q6FmGGX&Of?+Q$R%3U?43VkBGz zKzVk9nxQ-hJlt?K!R;YV6j+*#i2ZUD$NcR|-n0?34Njg^Y#})`t@A8+ZnZZ!`KLYcGP)00-6t5C^vO zI($WpDuNn;if8i<`=tU6p_56Jq+RHQ;UhYLECoYciYsLYE*>Y?V}7WRq)cQHRkJ*d z{Z~=QL6TQ7#iG)B{5jIr!h1GAASJs;Nz)%F6&VN`j&ulc!Rs0UyekAaeosd?7?dNy zp(sQ0Y=54>DX+vuAh8@QPX~S+`UzJN@^E7dmn#(WF@&tmsi??w_vzup{;T0IA=-}e zp%X`wqczV~7T{tam674YUc3YA9+dX+lCnvlqUI*{MA#EM$cqA6tqpm-M;K|X zE6@f;9UhpNnAo#~YC-2Ve%IqYvhVVnAVHqQ`pzJbONQvupbCYOXEhjvl^Qg6kmu0z zRs<6&G~HOfOBUr5#1o__0|y}LGP)lGCblVdz8%0G$va$OfbREbF#2Tx3Y0e4}3ctY& zRTz5N;Xpi^5Mv>n5l;dV;4R|tu2M5T-qWzUyc|G3oh^%@GQX6mjZPzN@p!SCX!YRu z^9u?R0|&~GW4tx!bM+#76LL}TXaoc_XbIjUy>ztCK|M_%U?R_n!J~j(G5kIG4a`2o z;t)ZTs9lgC_JR_EfHXyn+1m1q!cL9(8)#42!g3L!L9$-~>ICQj`@!8&;aPupa3&DJ zW5u?eJ2|q(VBr50K8Me7o`bnjx`A!_xR5=VvR;E*3pSkhy_c6TJ0JCL9~wUf^erdQ z2nfv0$kLEV`sC*e>U+(mn*Jt}4kuawFdw?D#ziQ_pxCE|&~|F1Jy%;~ zKlGHSzj0`PGvwhn?#=8~%ra?P%NjwCa+}Ro=t@`|kBYI4fq?;HW@Tg;DbM2BrLjwrGPFo~cUP|lAb%|URGLuvGT zZ!x~EO+e^l@q$l>;qa&(1j^@MCI-(KXYwt=385f>1X%F|Au=cFA3Ao#7_-j>Ry#pi z&271W!zUl5+_H073uqTah!L_eK@NDMWDE@|Bx28?uC7kh2C(xWtJ;A+q2ig_a(+GY z>U$YG=pv>bh$jxFI4cB|Ng->=;c|20=%G4A?L$u<1XgFDGq4sg9vEd0)CrNo0XSP8 z^sqHqjz${@8mKo25@1>lO-(Ci#yYQs8$89#VE{t;fXzo6oWzm)87mIeZ&^}4R~(6M zSZ+$fua6B4!3cCPBwazYqiA5^5v)TQb25>cY_ecd@u~@=ZiFZZG}^<={TF~QK*AUx zbdS8p@4pp{CUY6TGMjrY`%sSbp` z4&Wjkm#z^G{A~k(rxSoegmwLxbCdkgJV0aI-!g<&qFVt@Nd@2C`ocLF(R1M7mP`hJ zY7_7@3h<-w*z)B0v*fw3*j(Tg(n;?_gBQ$#8Q!^;mewdL8q59-@`-ubrc#vcoHIav;M#UWrD1_s64@8SfM-VQg2u_uD8n zL32XIJD1)>Pzm6QaKogwja`xcQ zH0q|G%_3P1)j*@g!GGOJ+i=ltp%PMuXc218Dg;9RJ9h{hC4O6)=8rvV-v!W+P&1lB zyCLDd6o;pqk7!o7>v4gKZlrp@dN#3*V8zJGe{_DFf{iBOc)()xU~5TOe7 zz4xRfSQa%r-Q_d7Ko8I~{Os(U$em)vHfCT1sG<)5>w(zUgj7Aga=(AbHf?zXUSXcF z*y!j}h#iCx)zAq26#NQl8fj@#{hODv0IScouluDfP8jnOOpd~)tg@1{DUe%k zZhq9jTe@gy7|L8(P*~V-cM(@l1kORX4p!hb;@zO1*!MAOr_;cPpCGZYi4?9!zK)BA0_ZQ1PXVzE10D>hx1}x@pKanP$YDV^)m+ddbOYWmM*}ot3sq zXXVnQxul}7(X^DAvDt~KY$v3$$f_YGbIf`@v;Knoc;D)b|B95jE)}nN&lRWVtQKKa z_~$Jp=$HKhb)17=S`}KRIIOkftQkk)v>N1_vrPyCRVS6o2S&!mqB^5GMh^pfk^_)M zFg-VL$cH>0cIIcYs$bj`Yf_zy*D%CJ!~<^2ekdX}DfG}^n{yop<+}wL26=rh|k`D z@;xWTravIwE|q#)Hq3-gThN4r*eBBl+eo?0SVs?K*&%syrJlF6eC6YCe@OwY^+M>R z|1&RhZ;;6tJ4UOW>!9d>JtM9*{zy0X2)&z9rDE>`bZU4}FEZArk9P|Ty92IujgGFA z&d|-b{tac$(6((io2L?e$?VXVPobny+na&cu~GLujc@h$8RooRYaY>#k{tImNL@mM zlzDs!a1xfe^8FVkl72++zA}%ggkz;K;@Ja5#5_y14{s;|J(fu=`tlViJr|UghBfO-aJ?l_u?@gf&O)B^$!guw2udfZGFWt?osJBPO8JJd38i zZdcH=iD^yxCt(LNT%J;ExN5S3^oE-Hy^P4i&sdHty8pSTyJ&i{nhvi4$E! zi3AFux*pO&aF9*cH*DTWWyCXTkYf|+1saVtg-Pzr6<9|QcWZj=rMD1S*kedo*gCNy zv45D%aiPByq02HKt=J6+OkbT?7I>ujODhZNUtq-e00KN0tq$@pN-f^EyrGG67=mFB zyt$MGZk`{nD_wr=Z3;3_zTH$sT4yy~YImID-L>aeIN=s*Y!rZEqC$2wgD9296`Plp zM&!g^Bny|WXvcr^&DVy=6Model: \"sequential\"\n", + "\n" + ], + "text/plain": [ + "\u001b[1mModel: \"sequential\"\u001b[0m\n" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "text/html": [ + "

┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓\n",
+              "┃ Layer (type)                    ┃ Output Shape           ┃       Param # ┃\n",
+              "┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩\n",
+              "│ conv2d (Conv2D)                 │ (None, 26, 26, 32)     │           320 │\n",
+              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+              "│ max_pooling2d (MaxPooling2D)    │ (None, 13, 13, 32)     │             0 │\n",
+              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+              "│ conv2d_1 (Conv2D)               │ (None, 11, 11, 64)     │        18,496 │\n",
+              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+              "│ max_pooling2d_1 (MaxPooling2D)  │ (None, 5, 5, 64)       │             0 │\n",
+              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+              "│ dropout (Dropout)               │ (None, 5, 5, 64)       │             0 │\n",
+              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+              "│ flatten (Flatten)               │ (None, 1600)           │             0 │\n",
+              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+              "│ dense (Dense)                   │ (None, 10)             │        16,010 │\n",
+              "└─────────────────────────────────┴────────────────────────┴───────────────┘\n",
+              "
\n" + ], + "text/plain": [ + "┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓\n", + "┃\u001b[1m \u001b[0m\u001b[1mLayer (type) \u001b[0m\u001b[1m \u001b[0m┃\u001b[1m \u001b[0m\u001b[1mOutput Shape \u001b[0m\u001b[1m \u001b[0m┃\u001b[1m \u001b[0m\u001b[1m Param #\u001b[0m\u001b[1m \u001b[0m┃\n", + "┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩\n", + "│ conv2d (\u001b[38;5;33mConv2D\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m26\u001b[0m, \u001b[38;5;34m26\u001b[0m, \u001b[38;5;34m32\u001b[0m) │ \u001b[38;5;34m320\u001b[0m │\n", + "├─────────────────────────────────┼────────────────────────┼───────────────┤\n", + "│ max_pooling2d (\u001b[38;5;33mMaxPooling2D\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m13\u001b[0m, \u001b[38;5;34m13\u001b[0m, \u001b[38;5;34m32\u001b[0m) │ \u001b[38;5;34m0\u001b[0m │\n", + "├─────────────────────────────────┼────────────────────────┼───────────────┤\n", + "│ conv2d_1 (\u001b[38;5;33mConv2D\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m11\u001b[0m, \u001b[38;5;34m11\u001b[0m, \u001b[38;5;34m64\u001b[0m) │ \u001b[38;5;34m18,496\u001b[0m │\n", + "├─────────────────────────────────┼────────────────────────┼───────────────┤\n", + "│ max_pooling2d_1 (\u001b[38;5;33mMaxPooling2D\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m5\u001b[0m, \u001b[38;5;34m5\u001b[0m, \u001b[38;5;34m64\u001b[0m) │ \u001b[38;5;34m0\u001b[0m │\n", + "├─────────────────────────────────┼────────────────────────┼───────────────┤\n", + "│ dropout (\u001b[38;5;33mDropout\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m5\u001b[0m, \u001b[38;5;34m5\u001b[0m, \u001b[38;5;34m64\u001b[0m) │ \u001b[38;5;34m0\u001b[0m │\n", + "├─────────────────────────────────┼────────────────────────┼───────────────┤\n", + "│ flatten (\u001b[38;5;33mFlatten\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m1600\u001b[0m) │ \u001b[38;5;34m0\u001b[0m │\n", + "├─────────────────────────────────┼────────────────────────┼───────────────┤\n", + "│ dense (\u001b[38;5;33mDense\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m10\u001b[0m) │ \u001b[38;5;34m16,010\u001b[0m │\n", + "└─────────────────────────────────┴────────────────────────┴───────────────┘\n" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "text/html": [ + "
 Total params: 34,826 (136.04 KB)\n",
+              "
\n" + ], + "text/plain": [ + "\u001b[1m Total params: \u001b[0m\u001b[38;5;34m34,826\u001b[0m (136.04 KB)\n" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "text/html": [ + "
 Trainable params: 34,826 (136.04 KB)\n",
+              "
\n" + ], + "text/plain": [ + "\u001b[1m Trainable params: \u001b[0m\u001b[38;5;34m34,826\u001b[0m (136.04 KB)\n" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "text/html": [ + "
 Non-trainable params: 0 (0.00 B)\n",
+              "
\n" + ], + "text/plain": [ + "\u001b[1m Non-trainable params: \u001b[0m\u001b[38;5;34m0\u001b[0m (0.00 B)\n" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], + "source": [ + "# Создание модели сверточной нейронной сети\n", + "model = Sequential()\n", + "model.add(layers.Conv2D(32, kernel_size=(3, 3), activation=\"relu\", input_shape=input_shape))\n", + "model.add(layers.MaxPooling2D(pool_size=(2, 2)))\n", + "model.add(layers.Conv2D(64, kernel_size=(3, 3), activation=\"relu\"))\n", + "model.add(layers.MaxPooling2D(pool_size=(2, 2)))\n", + "model.add(layers.Dropout(0.5))\n", + "model.add(layers.Flatten())\n", + "model.add(layers.Dense(num_classes, activation=\"softmax\"))\n", + "\n", + "model.summary()" + ] + }, + { + "cell_type": "code", + "execution_count": 6, + "metadata": { + "id": "q_h8PxkN9m0v" + }, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Epoch 1/15\n", + "\u001b[1m106/106\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m21s\u001b[0m 184ms/step - accuracy: 0.7694 - loss: 0.7610 - val_accuracy: 0.9437 - val_loss: 0.2013\n", + "Epoch 2/15\n", + "\u001b[1m106/106\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m17s\u001b[0m 161ms/step - accuracy: 0.9426 - loss: 0.1908 - val_accuracy: 0.9685 - val_loss: 0.1134\n", + "Epoch 3/15\n", + "\u001b[1m106/106\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m18s\u001b[0m 173ms/step - accuracy: 0.9609 - loss: 0.1283 - val_accuracy: 0.9747 - val_loss: 0.0851\n", + "Epoch 4/15\n", + "\u001b[1m106/106\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m22s\u001b[0m 210ms/step - accuracy: 0.9688 - loss: 0.1022 - val_accuracy: 0.9785 - val_loss: 0.0708\n", + "Epoch 5/15\n", + "\u001b[1m106/106\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m21s\u001b[0m 201ms/step - accuracy: 0.9730 - loss: 0.0871 - val_accuracy: 0.9808 - val_loss: 0.0602\n", + "Epoch 6/15\n", + "\u001b[1m106/106\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m21s\u001b[0m 200ms/step - accuracy: 0.9758 - loss: 0.0779 - val_accuracy: 0.9823 - val_loss: 0.0547\n", + "Epoch 7/15\n", + "\u001b[1m106/106\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m22s\u001b[0m 206ms/step - accuracy: 0.9781 - loss: 0.0707 - val_accuracy: 0.9820 - val_loss: 0.0515\n", + "Epoch 8/15\n", + "\u001b[1m106/106\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m21s\u001b[0m 194ms/step - accuracy: 0.9805 - loss: 0.0637 - val_accuracy: 0.9858 - val_loss: 0.0468\n", + "Epoch 9/15\n", + "\u001b[1m106/106\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m20s\u001b[0m 191ms/step - accuracy: 0.9813 - loss: 0.0611 - val_accuracy: 0.9865 - val_loss: 0.0419\n", + "Epoch 10/15\n", + "\u001b[1m106/106\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m20s\u001b[0m 190ms/step - accuracy: 0.9816 - loss: 0.0574 - val_accuracy: 0.9865 - val_loss: 0.0402\n", + "Epoch 11/15\n", + "\u001b[1m106/106\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m20s\u001b[0m 190ms/step - accuracy: 0.9831 - loss: 0.0531 - val_accuracy: 0.9873 - val_loss: 0.0401\n", + "Epoch 12/15\n", + "\u001b[1m106/106\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m21s\u001b[0m 194ms/step - accuracy: 0.9840 - loss: 0.0503 - val_accuracy: 0.9880 - val_loss: 0.0367\n", + "Epoch 13/15\n", + "\u001b[1m106/106\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m20s\u001b[0m 190ms/step - accuracy: 0.9846 - loss: 0.0476 - val_accuracy: 0.9882 - val_loss: 0.0372\n", + "Epoch 14/15\n", + "\u001b[1m106/106\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m21s\u001b[0m 195ms/step - accuracy: 0.9845 - loss: 0.0479 - val_accuracy: 0.9880 - val_loss: 0.0360\n", + "Epoch 15/15\n", + "\u001b[1m106/106\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m21s\u001b[0m 194ms/step - accuracy: 0.9852 - loss: 0.0453 - val_accuracy: 0.9888 - val_loss: 0.0330\n" + ] + }, + { + "data": { + "text/plain": [ + "" + ] + }, + "execution_count": 6, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "# Компиляция и обучение модели\n", + "batch_size = 512\n", + "epochs = 15\n", + "model.compile(loss=\"categorical_crossentropy\", optimizer=\"adam\", metrics=[\"accuracy\"])\n", + "model.fit(X_train, y_train, batch_size=batch_size, epochs=epochs, validation_split=0.1)" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "HL2_LVga1C3l" + }, + "source": [ + "### 6) Оценка качества модели на тестовых данных\n", + "\n", + "Проводим финальную оценку обученной модели на независимой тестовой выборке, получая значения функции потерь и точности классификации." + ] + }, + { + "cell_type": "code", + "execution_count": 7, + "metadata": { + "id": "81Cgq8dn9uL6" + }, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "\u001b[1m313/313\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 4ms/step - accuracy: 0.9884 - loss: 0.0409\n", + "Loss on test data: 0.04092026501893997\n", + "Accuracy on test data: 0.9883999824523926\n" + ] + } + ], + "source": [ + "# Оценка качества работы обученной модели на тестовой выборке\n", + "scores = model.evaluate(X_test, y_test)\n", + "print('Loss on test data:', scores[0])\n", + "print('Accuracy on test data:', scores[1])" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "KzrVY1SR1DZh" + }, + "source": [ + "### 7) Демонстрация работы модели на отдельных примерах\n", + "\n", + "Визуализируем результаты распознавания для двух тестовых изображений, сравнивая предсказания модели с истинными метками." + ] + }, + { + "cell_type": "code", + "execution_count": 8, + "metadata": { + "id": "dbfkWjDI1Dp7" + }, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 93ms/step\n", + "NN output: [[1.8653100e-06 8.5978480e-10 4.9378517e-08 3.8702552e-11 2.3658897e-05\n", + " 1.0921732e-09 9.9997437e-01 5.6489594e-11 7.1016423e-08 2.4439044e-09]]\n" + ] + }, + { + "data": { + "image/png": "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", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Real mark: 6\n", + "NN answer: 6\n", + "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 44ms/step\n", + "NN output: [[7.1973699e-12 5.2415072e-09 2.9768824e-08 9.9999547e-01 8.1457769e-14\n", + " 2.3912532e-08 1.0659815e-14 1.0085358e-09 6.9545116e-09 4.5778688e-06]]\n" + ] + }, + { + "data": { + "image/png": "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", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Real mark: 3\n", + "NN answer: 3\n" + ] + } + ], + "source": [ + "# Визуализация результатов распознавания для двух тестовых изображений\n", + "\n", + "for n in [3,26]:\n", + " result = model.predict(X_test[n:n+1])\n", + " print('NN output:', result)\n", + "\n", + " plt.imshow(X_test[n].reshape(28,28), cmap=plt.get_cmap('gray'))\n", + " plt.show()\n", + " print('Real mark: ', np.argmax(y_test[n]))\n", + " print('NN answer: ', np.argmax(result))" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "YgiVGr5_1D3u" + }, + "source": [ + "### 8) Детальный анализ качества классификации\n", + "\n", + "Генерируем подробный отчет о качестве классификации и строим матрицу ошибок для визуального анализа работы модели по каждому классу." + ] + }, + { + "cell_type": "code", + "execution_count": 9, + "metadata": { + "id": "7MqcG_wl1EHI" + }, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "\u001b[1m313/313\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 4ms/step\n", + " precision recall f1-score support\n", + "\n", + " 0 1.00 0.99 1.00 1001\n", + " 1 0.99 1.00 0.99 1143\n", + " 2 0.99 0.99 0.99 987\n", + " 3 0.99 0.99 0.99 1023\n", + " 4 0.99 0.99 0.99 974\n", + " 5 1.00 0.98 0.99 907\n", + " 6 0.99 0.99 0.99 974\n", + " 7 0.98 0.99 0.99 1032\n", + " 8 0.98 0.98 0.98 1006\n", + " 9 0.98 0.99 0.98 953\n", + "\n", + " accuracy 0.99 10000\n", + " macro avg 0.99 0.99 0.99 10000\n", + "weighted avg 0.99 0.99 0.99 10000\n", + "\n" + ] + }, + { + "data": { + "image/png": "iVBORw0KGgoAAAANSUhEUgAAAgMAAAGwCAYAAAA0bWYRAAAAOnRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjEwLjcsIGh0dHBzOi8vbWF0cGxvdGxpYi5vcmcvTLEjVAAAAAlwSFlzAAAPYQAAD2EBqD+naQAAe/FJREFUeJzt3Xd4FNX6wPHv7ibZzaYHUiGB0HsRFAMqoggqIogNRaUJPzWoiCAigqBCBAURC5ar4PWCwr0KKveKRFSK9BKlSQtCCKSRsunJ7s7vj5iFFSIJm2SG7Pt5nnme7OyUd89MZt4558yMTlEUBSGEEEK4Lb3aAQghhBBCXZIMCCGEEG5OkgEhhBDCzUkyIIQQQrg5SQaEEEIINyfJgBBCCOHmJBkQQggh3JyH2gG4wm63c/r0afz8/NDpdGqHI4QQopoURSEvL4/IyEj0+tq7Pi0uLqa0tNTl5Xh5eWEymWogIm25opOB06dPExUVpXYYQgghXJScnEzjxo1rZdnFxcXENPElNd3m8rLCw8M5fvx4vUsIruhkwM/PD4BFGzrg7WtQOZpzllzVVO0QhBDiimCljE38z3E8rw2lpaWkpts4sasp/n6XX/tgybPTpNsflJaWSjKgJRVNA96+Bsx+2kkGPHSeaocghBBXhj8fiF8XTb2+fjp8/S5/PXbqb3P0FZ0MCCGEEFVlU+zYXHgbj02x11wwGiPJgBBCCLdgR8HO5WcDrsyrdXJroRBCCOHmpGZACCGEW7Bjx5WKftfm1jZJBoQQQrgFm6JgUy6/qt+VebVOmgmEEEIINyc1A0IIIdyCdCCsnCQDQggh3IIdBZskAxclzQRCCCGEm5OaASGEEG5BmgkqV6+TgdJ8HTvfCuaPBDNFZw00bFdK7NSzhHYqAaAw08D214M59Ys3JRY9EVcX02taJgFNrY5lfPtQBGe2ezstt+1QC9e/nFmrsQ8ckck9j6cTHGIl6YA3773YiEOJ5lpd59/p0COfe5/IoGXHQhqEW5kxqilb1gSoFk8FKaeq0VI53fFIJgMeOUtYVPkb5E4cMrH0zTB2/uSvSjzn01I5aXVfAm2VU3XI3QSVq9fNBBumhpDyizd9Xs/gntWnaNSriP+OiKAg1YCiwNonwrAke9DvvTTuXpWCb6SV/46IoKzQ+fnTbe6z8NAvJxxDj+fO1mrcve/MZuxLp1k6P5y4/q1IOmBi1rIkAhqU1ep6/47JbCdpv4l3Xqidt4pdDimnqtFaOWWc8eST2RGMu7UVT97Wil9/8WXG4j9o0qpYlXgqaK2ctLgvgfbKSdQMTSQD7777Lk2bNsVkMtGjRw+2b9/u8jKtxTqOr/Whx6SzRFxdTEATK92fyiagSRkHPvcn9w9P0hNNXDczk9BOJQQ2K+P6mZlYi/UcW+3rtCwPbwVziM0xePnWbnY4ZGwma5YFs3Z5MCePmFg4uTElRTr6P5BVq+v9Ozt/8ufTuRFs1siVCUg5VZXWymlbQgA7fvTn9HEjKUlGlsyJoLhAT5tuBarEU0Fr5aTFfQm0V07VYa+Bob5SPRlYvnw5EyZM4KWXXmL37t107tyZ/v37k56e7tJy7VZQbDoMRucTt8GokLrLhL28hhKP877X6cHgVf79+Y5+48un1zTh3wMas/2NIKxFtffmKg9POy07FbJ747nXeSqKjj0b/WjXrbDW1nulkXKqGq2Xk16v0HtQNkaznYM7fVSLQ+vlpBVXejnZ/rybwJWhvlI9GZg/fz5jxoxh5MiRtGvXjvfffx+z2cwnn3zi0nK9fBXCuhaz+70gCtIM2G1w5Gtf0hONFGYYCGxWhm9kGdvnBVOSq8dWCokfBlCQ6kFhxrnXIbe4I58+b6Qz8LPTdPm/HI587cePE0Nd/dmV8g+2YfCAnAzn7hzZmR4EhVgrmcv9SDlVjVbLqWmbIlYd2cvqP37jqddO8fLoppw8ot774bVaTlpzpZeTTXF9qK9U7UBYWlrKrl27mDJlimOcXq+nb9++bNmy5YLpS0pKKCkpcXy2WCx/u/w+r6ezfkoIS69vgs6g0LBdCc3vyCdznxG9J9zyThobXgjh06ubojMoNOpZRNQNhZyf/LUdmuf4O7h1GeYQK/8dHonlpAf+0drf+YXQolPHjDxxSyvMfjauvyOXiW+dZNKQFqomBEK4M1WTgczMTGw2G2FhYU7jw8LC+P333y+YPj4+npkzZ1Z5+f7RVgYuPUNZoY6yfD3mUBs/PB2KX1T5STykQyl3f5NCaZ4OW5kO72A7K++JJKRDSaXLDO1c/l3uCc9aSQYsWQZsVgj8S5Yd1NBKdka9vvmjWqScqkar5WQt03P6DyMAR/eaad2lkMGPZrBwcpQq8Wi1nLTmSi8nV9v9pc+ARkyZMoXc3FzHkJycXKX5PM0K5lAbJbl6Tm3ypunNzh2VvPwUvIPt5P7hQeY+I037Vt72dfagFwDmENvl/5C/YS3Tc+Q3M12vO1cjodMpdLkunwO7tH/rTl2RcqqaK6WcdDrw9FKvDvZKKSe1XenlZEeHzYXBTu31F1Obqqlcw4YNMRgMpKWlOY1PS0sjPDz8gumNRiNGo7HKy0/e6A0KBMSUYTnpybY5wQQ2K6P13eU7ctJ3PpiCbfhGWMk67MXmWQ1o0reQxtcVAWA56cHRb32J6l2IKdDO2UNebJndgIiri2jQptSFX/73vvqwIRMXJHP4VzOH9pi5a0wGJrOdtV8E19o6L8VkthEZc+43h0eV0qx9EXk5BjJSvFSJScqparRWTiOnnGHHj35kpHjh7Wujz105dOqZz9QHm6kSTwWtlZMW9yXQXjmJmqFqMuDl5UW3bt1Yt24dgwcPBsBut7Nu3TrGjRvn8vJL8/RsnxdMQaoHxkAbMf0KuGZCFnrP8u8LMwxsiW9A0VkD5hArLQfnc9UT2Y759Z4KKZu92ftpANZCHT4RNmL6FzhNUxvWfxNEQAMbj0xKJSjEStJ+b6YOiyEn07NW1/t3WnUu4vUvjzk+PzbzNABrlwcx75loVWKScqoarZVTYEMrkxaeJDjUSmGegeMHTUx9sBm7N/hdeuZapLVy0uK+BNorp+qwK+WDK/PXVzpFUfeRSsuXL2f48OF88MEHXHPNNSxYsIAVK1bw+++/X9CX4K8sFgsBAQEs2d0Zs5/hb6etSx+2UvcKRwghrhRWpYyf+Zrc3Fz8/WvnKZQV54pt+8Px9bv81vH8PDs92qfWaqxqUb3Hx/33309GRgbTp08nNTWVLl26sGbNmksmAkIIIYSoGaonAwDjxo2rkWYBIYQQojIVHQFdmb++0kQyIIQQQtQ2u6LDrlz+Cd2VebXuirq1UAghhBA1T2oGhBBCuAVpJqicJANCCCHcgg09NhcqxGvnUXPaIMmAEEIIt6C42GdAkT4DQgghhKivpGZACCGEW5A+A5WTZEAIIYRbsCl6bIoLfQbq8eOIpZlACCGEcHNSMyCEEMIt2NFhd+Ea2E79rRqQZEAIIYRbkD4DlasXycCSq5riodPO6zO/P52odggX6B/ZRe0QhBBCaFS9SAaEEEKIS3G9A6E0EwghhBBXtPI+Ay68qKgeNxPI3QRCCCGEm5OaASGEEG7B7uK7Cerz3QRSMyCEEMItVPQZcGWojg0bNjBw4EAiIyPR6XSsWrXK6XtFUZg+fToRERF4e3vTt29fjhw54jRNVlYWw4YNw9/fn8DAQEaPHk1+fr7TNL/99hvXX389JpOJqKgo5s6dW+2ykWRACCGEW7Cjd3mojoKCAjp37sy777570e/nzp3LwoULef/999m2bRs+Pj7079+f4uJixzTDhg1j//79JCQksHr1ajZs2MDYsWMd31ssFvr160eTJk3YtWsXr7/+OjNmzODDDz+sVqzSTCCEEELUgttuu43bbrvtot8pisKCBQt48cUXGTRoEAD//Oc/CQsLY9WqVQwdOpSDBw+yZs0aduzYQffu3QF4++23uf3223njjTeIjIxk6dKllJaW8sknn+Dl5UX79u1JTExk/vz5TknDpUjNgBBCCLdgU3QuD1B+NX7+UFJSUu1Yjh8/TmpqKn379nWMCwgIoEePHmzZsgWALVu2EBgY6EgEAPr27Yter2fbtm2OaW644Qa8vLwc0/Tv359Dhw6RnZ1d5XgkGRBCCOEWbH92IHRlAIiKiiIgIMAxxMfHVzuW1NRUAMLCwpzGh4WFOb5LTU0lNDTU6XsPDw+Cg4OdprnYMs5fR1VIM4EQQghRDcnJyfj7+zs+G41GFaOpGZIMCCGEcAt2RY/dhScQ2v98AqG/v79TMnA5wsPDAUhLSyMiIsIxPi0tjS5dujimSU9Pd5rParWSlZXlmD88PJy0tDSnaSo+V0xTFdJMIIQQwi3UVDNBTYiJiSE8PJx169Y5xlksFrZt20ZsbCwAsbGx5OTksGvXLsc0P/74I3a7nR49ejim2bBhA2VlZY5pEhISaN26NUFBQVWOR5IBYOCITD7ddoBvk37jrdVHaN2lsMaWvXerD9MfieGBru3pH9mFzd8FOH2/6X8BTBnajHvad6B/ZBeO7fOudFmKAlOHNbvoctJPeTLt4RjubNaJ+zq256OXI7FZa+xn0KFHPjM/Pc6y3fv5/vSvxN6aW3MLd0FtbjuJqfbI/nRpWi0j0FY5aVl+fj6JiYkkJiYC5Z0GExMTOXnyJDqdjvHjx/Pqq6/yzTffsHfvXh555BEiIyMZPHgwAG3btuXWW29lzJgxbN++nV9++YVx48YxdOhQIiMjAXjwwQfx8vJi9OjR7N+/n+XLl/PWW28xYcKEasXq9slA7zuzGfvSaZbODyeufyuSDpiYtSyJgAZll565CooL9TRrX8S42acq/b79NQWMfuH0JZe18qMQdBd5NLbNBtMeaUZZqZ43vznCpLdOkrAimE9fj7hw4stkMttJ2m/inRca19gyXVXb205iqj2yP12aFssItFdO1WHHtTsK7NVc386dO+natStdu3YFYMKECXTt2pXp06cD8Nxzz/Hkk08yduxYrr76avLz81mzZg0mk8mxjKVLl9KmTRtuvvlmbr/9dq677jqnZwgEBASwdu1ajh8/Trdu3Xj22WeZPn16tW4rBJX7DGzYsIHXX3+dXbt2cebMGVauXOnIiOrKkLGZrFkWzNrlwQAsnNyYa2620P+BLFa8E3aJuS/t6pvyuPqmvEq/73tP+a0fqclelU4DcGyfN19+EMLb3x3mgS4dnL7bvd6Pk4dNvLZ8P0EhVpoDjzx3ho9nRfLws6l4ern+CM2dP/mz8yfX2shqWm1vO4mp9sj+dGlaLCPQXjlVx+U8OOiv81fHjTfeiPI3bzrU6XS8/PLLvPzyy5VOExwczLJly/52PZ06dWLjxo3Viu2vVK0ZuNTTmWqbh6edlp0K2b3RzzFOUXTs2ehHu27aqfYqLtTxWlwT4madIjj0wrr/Azt9aNqmmKCQc991vzGPwjwDJw6ZLpi+PtDitpOYrlxSTlUj5VR/qVoz8HdPZ6oL/sE2DB6Qk+FcDNmZHkS1qP5DJGrLBzMa0a57AT1vtVz0++wMD4JCnKvoAhuWOb6rj7S47SSmK5eUU9Vc6eV0Oe8X+Ov89dUVdaYoKSlxetKTxXLxk2N9suV7fxJ/8eO9tYfUDkUIIa5odnTYuUjHq2rMX19dUclAfHw8M2fOrLHlWbIM2KwQGOJc9R7U0KqZK+rEX/w484cXQ9p0dBr/ypimdOhRwOtfHiUoxMqhPT5O3+dkegI4NR3UJ1rcdhLTlUvKqWqu9HKSmoHKXVG/bMqUKeTm5jqG5ORkl5ZnLdNz5DczXa8718FPp1Pocl0+B3aZXQ23Rtw/Lo331x1iUcK5AeD/ZqTw7JsnAWjXvYA/fjeRk3nun3H3Bj/MfjaiWxVfdLlXOi1uO4npyiXlVDVSTvWX9lO58xiNxhp/7ONXHzZk4oJkDv9q5tAeM3eNycBktrP2i+AaWX5RgZ7Tx8/FnJrsxbF93vgFWgltXIYl20BGihdn08o3RfKx8mmDQssIDrU6hr8KbVRGeHQpAFf1ziO6VTFzn4xm9Iunyc7wZMmccAaOyMTL6PqdBAAms43ImFLH5/CoUpq1LyIvpzx+NdT2tpOYao/sT5emxTIC7ZVTdbj64KCafOiQ1lxRyUBtWP9NEAENbDwyKZWgECtJ+72ZOizGUc3uqsO/mnnunhaOzx/MaATALfdlMXHBSbauDWDeM9GO7+MfbwrAQxNSeXhi1V4yYTDAy/9M4u3no3hmYCtMZjt9781i+KQzNfIbAFp1LuL1L485Pj82s/y5CGuXBznFX5dqe9tJTLVH9qdL02IZgfbKqTrsig674kKfARfm1Tqd8nc3Qday/Px8jh49CkDXrl2ZP38+ffr0ITg4mOjoS+/sFouFgIAAbmQQHjrt7Ijfn05UO4QL9I/sonYIQghxAatSxs98TW5ursvP+69Mxbli7o7r8fa9/Gvgonwrz129sVZjVYuqNQM7d+6kT58+js8Vj08cPnw4S5YsUSkqIYQQ9ZHdxWYCVx5YpHWqJgOXejqTEEIIUVNcf2th/U0G6u8vE0IIIUSVuH0HQiGEEO7Bhg6bCw8OcmVerZNkQAghhFuQZoLK1d9fJoQQQogqkZoBIYQQbsGGa1X9tpoLRXMkGRBCCOEWpJmgcpIMCCGEcAvyoqLK1d9fJoQQQogqkZoBIYQQbkFBh92FPgOK3FoohBBCXNmkmaBy9feXCSGEEKJKpGagFmjxDYEP/H5a7RAu8HmbSLVDEEK4EXmFceUkGRBCCOEWbC6+tdCVebWu/v4yIYQQQlSJ1AwIIYRwC9JMUDlJBoQQQrgFO3rsLlSIuzKv1tXfXyaEEEKIKpGaASGEEG7BpuiwuVDV78q8WifJgBBCCLcgfQYqJ8mAEEIIt6C4+NZCRZ5AKIQQQoj6SmoGhBBCuAUbOmwuvGzIlXm1TpIBIYQQbsGuuNbub1dqMBiNkWYCIYQQws1JzQAwcEQm9zyeTnCIlaQD3rz3YiMOJZpVieWORzIZ8MhZwqJKAThxyMTSN8PY+ZN/ra2zLF/Hbwv9OPWDiZKzBoLalnHV1FwadCwDKn+hUJdJubQdXeA0zlYKa+8LIed3T25dmU5QW2utxd2hRz73PpFBy46FNAi3MmNUU7asCai19VWVlvYnrcaktW13/7g0et2eS1SLEkqL9RzYaebjWRGcOmaSmP7GfePSGP1CKis/asj7LzVSO5xLsrvYgdCVebWu/v6yKup9ZzZjXzrN0vnhxPVvRdIBE7OWJRHQoEyVeDLOePLJ7AjG3dqKJ29rxa+/+DJj8R80aVVca+vcPi2Q1M1GYufkcNs36YT3KuGnkQ0oTCvfPQZvTHUaeszKBp1CVL8LY0p83R/vUFutxXo+k9lO0n4T77zQuE7WVxVa25+0GpPWtl2n2AK+XdKQ8Xe0ZMrQZhg8FGZ/noTRu2725SslpvO16lzIgIeySNqvneTkUuzoXB7qK1WTgfj4eK6++mr8/PwIDQ1l8ODBHDp0qE5jGDI2kzXLglm7PJiTR0wsnNyYkiId/R/IqtM4KmxLCGDHj/6cPm4kJcnIkjkRFBfoadOt4NIzXwZrMSSvNdFlooXQq0vxa2Kj45N5+EZbOfq5DwDeIXan4dSPJsJ6lOIb5XxQOr3BSOovRro+Z6mVWP9q50/+fDo3gs0aqA2ooLX9SasxaW3bTR3WjIQVwZw4bCLpgDfzxkcT1riMlp2KJKaLMJltTH7nBAsmNSYv16B2OKIGqJoMrF+/nri4OLZu3UpCQgJlZWX069ePgoLaOfH9lYennZadCtm90c8xTlF07NnoR7tuhXUSw9/R6xV6D8rGaLZzcKdPraxDsepQbDoMRueeMQaTQsYurwumL8rUc3q9iWZ3F14wfvu0QK6dk4PBVI972fwNLe5PWozpSuDjX57o5uVo50SnpZjGzU5h+zp/9py3X10JKp5A6MpQX6naZ2DNmjVOn5csWUJoaCi7du3ihhtuqPX1+wfbMHhAToZzMWRnehDVoqTW11+Zpm2KWPDtUbyMdooK9Lw8uiknj9ROVZynr0LDLqXsf88P/2bZmBraOfFfb84meuEbfWF15PFVZjx9FKL6nbs6URTYNiWQFkMLaNCxjPxT6h+s1KDF/UmLMWmdTqfw2MwU9m03c+KQt9rhANqKqfegbFp0LOLJ21uqGsflkD4DldNUB8Lc3FwAgoODL/p9SUkJJSXnDmAWS91UR9e1U8eMPHFLK8x+Nq6/I5eJb51k0pAWtZYQXDs3m20vBPJ173B0BoWgdmVEDygie7/nBdMmfelNkzsKMRjPjTv8mQ9lBTrajc2vlfiEqEvjZqfQpE0xzw5uoXYoDlqJKSSylMdfPs2Uoc0oK6m/J0Z3pJlkwG63M378eHr16kWHDh0uOk18fDwzZ86ssXVasgzYrBAY4tzjPaihlewM9YrGWqbn9B/lZ9uje8207lLI4EczWDg5qlbW5xdto++/zmIt1FGWr8M71M4vzwRd0CcgfacXecc96fVmttP4tG1enE30YkWnCKfx398TQpM7ioidk1MrcWuNFvcnLcakZXGzTtHjFgvP3tWczDMXNpOpQUsxtehURFCIlXe/P+wYZ/CAjtcWcOfITO5o2gm7XbtV6XZcfDdBPe5AqJmjQVxcHPv27WPTpk2VTjNlyhQmTJjg+GyxWIiKuvwTpLVMz5HfzHS9Ls9xW5NOp9Dluny+WdLgspdb03Q68PSq/XZ4D7OCh1mhNFfHmU1Gukx0rnlJ+o+Z4PalBLVxPrF0m2qh09N5js9F6QZ+frQBveZn06Bzaa3HrRVa3J+0GJM2KcTNSqHnrblMuqcFacnGS89S67QXU+JGX8b2aeU07tk3k0k+amLFuyGaTgQAFBfvCFAkGahd48aNY/Xq1WzYsIHGjSu/1choNGI01uw/xFcfNmTigmQO/2rm0B4zd43JwGS2s/aLizdV1LaRU86w40c/MlK88Pa10eeuHDr1zGfqg81qbZ1nNhpRAP8YK3knPEh83R//ZlaaDTnXwawsX8fJ7010nXxh04xPpHMNgoe5PHHxjbZiDrfXWtwms43ImHPJRnhUKc3aF5GXYyAjRZ0rKK3tT1qNSWvbbtzsFPrclc2MkTEU5esJCim/7bIgz0BpsTrV4VqMqajAcEGfheJCPXnZF47XInlrYeVUTQYUReHJJ59k5cqV/Pzzz8TExNR5DOu/CSKggY1HJqUSFGIlab83U4fFkJN5YXt5XQhsaGXSwpMEh1opzDNw/KCJqQ82Y/eG2uu1W5av49f5/hSmGvAKtBN1SzGdnrGgP68ITvzXGxRoMkD925oqtOpcxOtfHnN8fmzmaQDWLg9i3jPRqsSktf1JqzFpbdsNHHEWgDe+OuY0/o3xUSSsUCdp0mJMov7SKYqi2n1gTzzxBMuWLePrr7+mdevWjvEBAQF4e186y7RYLAQEBHAjg/DQqXdguxI88PtptUO4QGVPNhRCuA+rUsbPfE1ubi7+/rXzpNWKc8VdCSPx9Ln8mqeyglJW3rK4VmNVi6o1A4sWLQLgxhtvdBq/ePFiRowYUfcBCSGEqLekmaByqjcTCCGEEEJdmuhAKIQQQtQ2V98vILcWCiGEEFc4aSaonDxCSgghhHBzUjMghBDCLUjNQOUkGRBCCOEWJBmonDQTCCGEEG5OagaEEEK4BakZqJzUDAghhHALCuduL7ycobpPxrHZbEybNo2YmBi8vb1p3rw5r7zyitMzdhRFYfr06URERODt7U3fvn05cuSI03KysrIYNmwY/v7+BAYGMnr0aPLza/aV8ZIMCCGEcAsVNQOuDNUxZ84cFi1axDvvvMPBgweZM2cOc+fO5e2333ZMM3fuXBYuXMj777/Ptm3b8PHxoX///hQXFzumGTZsGPv37ychIcHxUr+xY8fWWLmANBMIIYQQ1WKxOL+9tbI36m7evJlBgwYxYMAAAJo2bcrnn3/O9u3bgfJagQULFvDiiy8yaNAgAP75z38SFhbGqlWrGDp0KAcPHmTNmjXs2LGD7t27A/D2229z++2388YbbxAZWTPveJGaASGEEG6hpmoGoqKiCAgIcAzx8fEXXV/Pnj1Zt24dhw8fBuDXX39l06ZN3HbbbQAcP36c1NRU+vbt65gnICCAHj16sGXLFgC2bNlCYGCgIxEA6Nu3L3q9nm3bttVY2UjNgJvQ4hsCnzr6u9ohXGBhizZqhyAul06Dnbvk/SuaUlMdCJOTk53eWnixWgGA559/HovFQps2bTAYDNhsNmbNmsWwYcMASE1NBSAsLMxpvrCwMMd3qamphIaGOn3v4eFBcHCwY5qaIMmAEEIIUQ3+/v5VeoXxihUrWLp0KcuWLaN9+/YkJiYyfvx4IiMjGT58eB1EWnWSDAghhHALdX1r4aRJk3j++ecZOnQoAB07duTEiRPEx8czfPhwwsPDAUhLSyMiIsIxX1paGl26dAEgPDyc9PR0p+VarVaysrIc89cE6TMghBDCLSiKzuWhOgoLC9HrnU+zBoMBu90OQExMDOHh4axbt87xvcViYdu2bcTGxgIQGxtLTk4Ou3btckzz448/Yrfb6dGjx+UWxQWkZkAIIYSoBQMHDmTWrFlER0fTvn179uzZw/z58xk1ahQAOp2O8ePH8+qrr9KyZUtiYmKYNm0akZGRDB48GIC2bdty6623MmbMGN5//33KysoYN24cQ4cOrbE7CUCSASGEEG6i4uFBrsxfHW+//TbTpk3jiSeeID09ncjISP7v//6P6dOnO6Z57rnnKCgoYOzYseTk5HDdddexZs0aTCaTY5qlS5cybtw4br75ZvR6PXfffTcLFy687N9xMTpFuXK7u1osFgICAriRQXjoPNUOR1ST3E0gapTcTXBFsipl/MzX5ObmVqlT3uWoOFf0WPUUHj4X7/lfFdaCErYNXlirsapF+gwIIYQQbk6aCYQQQriFy+kE+Nf56ytJBoQQQrgFeWth5SQZEEII4RakZqBy0mdACCGEcHNSMyCEEMItKC42E9TnmgFJBoCBIzK55/F0gkOsJB3w5r0XG3Eo0SwxVeK+cWmMfiGVlR815P2XGrm8vJTt3uz6qAEZ+40UpHsyYNEpmt+S7/heUWDbWw3ZtzyQEoueyG5F9Hk5lcCmZY5pdrzXgOM/+ZB50ITeU+GxPUcuWE/eaQ9+mh7Oqa1mPM122g7JpefEDPQ1/F+gtW3XoUc+9z6RQcuOhTQItzJjVFO2rAlQLZ4KWiqnhyac4eFn05zGJR818mjvtqrEA9rcbvePS6PX7blEtSihtFjPgZ1mPp4VwaljpkvPrAEKrt3tWZ9vFHX7ZoLed2Yz9qXTLJ0fTlz/ViQdMDFrWRIBDcouPbMbxVShVedCBjyURdL+mvvnLyvSE9K2mBtnpF30+10fBpP4aRB9Xk7l/i9P4OFtZ9XIKKwl57J0W6mOlrfl0fHBnIsuw26Dbx5tjK1Mx70rTnDL62c48GUAWxc0rLHfAdrcdiaznaT9Jt55obFqMfyVFsvpj99NDO3S3jFMGNxStVhAm9utU2wB3y5pyPg7WjJlaDMMHgqzP0/C6G1TOzThIlWTgUWLFtGpUyfHG6BiY2P57rvv6jSGIWMzWbMsmLXLgzl5xMTCyY0pKdLR/4GsOo1D6zEBmMw2Jr9zggWTGpOXa6ix5TbtXUDshEya98u/4DtFgcQlwVwTd5bmt+TTsE0J/d44Q0GaB0kJvo7prh2fSddR2TRoXXLRdZzc5EPWUSP9550mpF1J+TqfyeS3fwVhK62xn6LJbbfzJ38+nRvBZg3UBlTQYjnZbJCd4ekYLNnqVpxqcbtNHdaMhBXBnDhsIumAN/PGRxPWuIyWnYrUDq1KKp5A6MpQX6maDDRu3JjXXnuNXbt2sXPnTm666SYGDRrE/v3762T9Hp52WnYqZPdGP8c4RdGxZ6Mf7boV1kkMV0JMFcbNTmH7On/2nBdbbbMke1KY4UFUzwLHOKOfnbDOxZzZ413l5aTu8aZB6xLMDc9dwURfX0BpvoGzRy7/iWTn0/K20xKtllOjmFKW7drHks0HmPz2CUIiazBLrKd8/Mv/n/Jyau7ioDbV9YuKriSqpr4DBw50+jxr1iwWLVrE1q1bad++/QXTl5SUUFJy7srPYrG4tH7/YBsGD8jJcC6G7EwPolpc/AqztmkxJoDeg7Jp0bGIJ2+v26rTwszycjA3tDqNNze0UphR9d23IMMDc4MLl3FuHa6XrVa3ndZosZx+3+PDG894c+qYkeDQMh6akMq8lUf4v5vaUFRwZZzo6ppOp/DYzBT2bTdz4lDVE3OhTZrpQGiz2fj3v/9NQUGB49WNfxUfH8/MmTPrODIRElnK4y+fZsrQZpSVuH03E1EP7fzp3HPmjx/05vc9Zj7bdoAbBubw/RcNVIxMu8bNTqFJm2KeHdxC7VCqzK7o0MlDhy5K9WRg7969xMbGUlxcjK+vLytXrqRdu3YXnXbKlClMmDDB8dlisRAVFXXZ67ZkGbBZITDE+YoxqKGV7GpcddYkLcbUolMRQSFW3v3+sGOcwQM6XlvAnSMzuaNpJ+z22vknOf/q3Sf0XBV/YaYHIe2Kq7wcnxArab85d3qsrNbhcmlx22nRlVBOBRYPTiUZiWwqNToXEzfrFD1usfDsXc3JPOOldjhVpigu3k1Qj28nUP0yr3Xr1iQmJrJt2zYef/xxhg8fzoEDBy46rdFodHQ2rBhcYS3Tc+Q3M12vy3OM0+kUulyXz4Fd6tzipMWYEjf6MrZPKx6/5dxwKNGbH78K4vFbWtVaIgDgH1WGOcRK8mYfx7iSPD1pv5qI6Fr1TkvhXYs4e8hI4dlzVb7Jv5jx8rUR3KJm2oa1uO206EooJ5PZRmSTUrLS5W2ozhTiZp2i5625PHdvc9KSa6a/jVCf6mm4l5cXLVqUVzN169aNHTt28NZbb/HBBx/Uyfq/+rAhExckc/hXM4f2mLlrTAYms521XwTXyfqvhJiKCgwXtAkWF+rJy75w/OUoLdCRe+Lc1YUl2ZOMA0ZMgTb8Iq10GZHFjvcaENi0FP+oMra+2RCfMCvNznsWQd5pD4pzDOSd9kCxQ8aB8oNUQJNSvHwUoq8rILhFCWufjaDX5AwKMzzYMj+ETg9l42GsuXRfa9sO/jyxxZxLeMKjSmnWvoi8HAMZKepc1WmtnMZMS2FrQgDppzxpEG7l4WfPYLPDz6uCVIkHtLndxs1Ooc9d2cwYGUNRvp6gkPJbQQvyDJQWq35teUnyOOLKqZ4M/JXdbnfqJFjb1n8TREADG49MSiUoxErSfm+mDoshJ1O9KwItxlSb0vd689VD0Y7PG2eHAdB2SC63zD1Dt7FZWIv0/PhiePlDh7oXMeiTZKeT+NYFIRz86twtWJ/fGQPAkH+dpPG1hegNMPCjU/w0PZx/39sED+/yhw5dOz6zRn+LFrddq85FvP7lMcfnx2aeBmDt8iDmPRNd2Wy1Smvl1DCijCnv/oFfkI3cLA/2b/dh/MBW5Gapd4jU4nYbOOIsAG98dcxp/Bvjo0hYoV7CW1WSDFROpyjqtYJMmTKF2267jejoaPLy8li2bBlz5szh+++/55Zbbrnk/BaLhYCAAG5kEB66+nmirM+eOvq72iFcYGGLNmqHIC6XToMH6vrcyFxDrEoZP/M1ubm5Ljf9VqbiXNF62fMYzJfftGErLOHQg6/VaqxqUbVmID09nUceeYQzZ84QEBBAp06dqpwICCGEEKJmqJoMfPzxx2quXgghhBuRuwkqp7k+A0IIIURtKE8GXOkzUIPBaIz2u38KIYQQolZJzYAQQgi3IHcTVE6SASGEEG5B+XNwZf76SpoJhBBCCDcnNQNCCCHcgjQTVE6SASGEEO5B2gkqJcmAEEII9+BizQD1uGZA+gwIIYQQbk5qBoQQQrgFeQJh5SQZEEII4RakA2HlJBkQqtHiGwLvPpiudggX+LJtqNohXBnq82VbTdLc2x119bpj3pVCkgEhhBDuQdG51glQagaEEEKIK5v0Gaic3E0ghBBCuDmpGRBCCOEe5KFDlZJkQAghhFuQuwkqV6Vk4JtvvqnyAu+8887LDkYIIYQQda9KycDgwYOrtDCdTofNZnMlHiGEEKL21OOqfldUKRmw2+21HYcQQghRq6SZoHIu3U1QXFxcU3EIIYQQtUupgaGeqnYyYLPZeOWVV2jUqBG+vr4kJSUBMG3aND7++OMaD1AIIYQQtavaycCsWbNYsmQJc+fOxcvLyzG+Q4cO/OMf/6jR4IQQQoiao6uBoX6qdjLwz3/+kw8//JBhw4ZhMBgc4zt37szvv/9eo8EJIYQQNUaaCSpV7ecMpKSk0KJFiwvG2+12ysrKaiSoujZwRCb3PJ5OcIiVpAPevPdiIw4lmlWJ5f5xafS6PZeoFiWUFus5sNPMx7MiOHXMpEo859NSOakRU1mBjgNv+XD6ByPFWXoC21rp/EIewR2tjmksxwzsm+dLxg5PFJsO/+ZWrn0rF3OkcydcRYFf/i+AtI1Grn07h0Z9S2sl5gruvu0upUOPfO59IoOWHQtpEG5lxqimbFkToEosFbR4LHhowhkefjbNaVzyUSOP9m6rUkSiplS7ZqBdu3Zs3LjxgvH/+c9/6Nq1a40EVZd635nN2JdOs3R+OHH9W5F0wMSsZUkENFAnsekUW8C3Sxoy/o6WTBnaDIOHwuzPkzB6q3vLptbKSY2Ydr/oR9pmL7rPsXDL11mE9Spl46hAitLK/43yTxpYPywIvxgrvT/Noe+qLNo8XoDeeOHlxNFPvWslxouRbXdpJrOdpP0m3nmhsSrrvxitHgv++N3E0C7tHcOEwS1VjadapGagUtVOBqZPn864ceOYM2cOdrudr776ijFjxjBr1iymT59+2YG89tpr6HQ6xo8ff9nLuBxDxmayZlkwa5cHc/KIiYWTG1NSpKP/A1l1GkeFqcOakbAimBOHTSQd8Gbe+GjCGpfRslORKvFU0Fo51XVMtmJISTDScWI+IVeX4dvERrtxBfhG20j6vPzEvn+BD+E3lNJxUgGB7az4RtuIvKkUUwPnI0jOQQ+OLDHTfVZejcd5Me6+7api50/+fDo3gs0q1wacT6vHApsNsjM8HYMl+wp6kG3FWwtdGeqpaicDgwYN4ttvv+WHH37Ax8eH6dOnc/DgQb799ltuueWWywpix44dfPDBB3Tq1Omy5r9cHp52WnYqZPdGP8c4RdGxZ6Mf7boV1mkslfHxL78KyMsxXGLK2qPFcqrrmOw2HYpNh+EvV/kGk0Lmbk8UO6Su98K3qZWNjwawuldDfrw/iJQfvJymtxbB9kn+dJmWhymk9p/fIduu/tDCsQCgUUwpy3btY8nmA0x++wQhkbXbxCXqxmU9Z+D6668nISGB9PR0CgsL2bRpE/369busAPLz8xk2bBgfffQRQUFBfzttSUkJFovFaXCFf7ANgwfkZDhnttmZHgSFWCuZq+7odAqPzUxh33YzJw7VXbXyX2mxnOo6Jk8fheAuZRxc5ENRuh7FBie/MXI20ZPiDD0lZ/VYC/Uc+ocP4deVct0/cmjUt4StTwWQsd3TsZzfXvOjQZcyIm+umwOobLv6QSvHgt/3+PDGM9FMfag5b09pTHh0CfNWHsHb58p48mzFK4xdGeqry67f2blzJwcPHgTK+xF069btspYTFxfHgAED6Nu3L6+++urfThsfH8/MmTMvaz1XonGzU2jSpphnB1/YYVPUvavnWNg11Y//9W6IzqAQ2M5K1IAScvZ7OA4SkTeV0HJEeTVuYFsrZ/d4krTcm5Bryjj9oxfpWz3p+1W2ir9CXIm0cizY+ZO/4+/jB735fY+Zz7Yd4IaBOXz/RQMVI6sieWthpaqdDJw6dYoHHniAX375hcDAQABycnLo2bMnX3zxBY0bV70DzhdffMHu3bvZsWNHlaafMmUKEyZMcHy2WCxERUVVK/7zWbIM2KwQ+JerkaCGVrIz1G0Hi5t1ih63WHj2ruZknvG69Ay1SIvlpEZMvtE2en+Wg7UQyvL1eIfa2faMPz6NbRgD7eg8FPyaO8fj18zK2d3lNQMZW70oSDbwTY+GTtNsfTqAht3K6P3PnBqPWbbdlU9Lx4K/KrB4cCrJSGTTErVDES6qdjPBo48+SllZGQcPHiQrK4usrCwOHjyI3W7n0UcfrfJykpOTefrpp1m6dCkmU9VulTEajfj7+zsNrrCW6Tnym5mu153ryKXTKXS5Lp8Du9S67UohbtYpet6ay3P3Nict2ahSHOdosZzUjMnDDN6hdkpzdaT94kXEzSXovSCog5X8484ns/w/PBy3FbYeU0jfVVnc/NW5AaDz8/l0n+1ak1dlZNtdybR3LPgrk9lGZJNSstI9Lz2xFkgHwkpVOw1fv349mzdvpnXr1o5xrVu35u233+b666+v8nJ27dpFeno6V111lWOczWZjw4YNvPPOO5SUlDg91Ki2fPVhQyYuSObwr2YO7TFz15gMTGY7a78IrvV1X8y42Sn0uSubGSNjKMrXExRSfqtVQZ6B0mKXXiXhEq2VkxoxpW7yAgX8YqzknzCw9w1f/GJsNL2r/B0drUYVsO3ZABp2NxHSo4zUTV6c+dmLGz7NAcAUYscUcuFyvSNs+DSuvc6Esu0uzWS2ERlzrh9HeFQpzdoXkZdjICNFnatxLR4LxkxLYWtCAOmnPGkQbuXhZ89gs8PPq/6+v5dW6JTywZX566tqJwNRUVEXfbiQzWYjMjKyysu5+eab2bt3r9O4kSNH0qZNGyZPnlwniQDA+m+CCGhg45FJqQSFWEna783UYTHkZKqT6Q4ccRaAN7465jT+jfFRJKxQ7+CttXJSIyZrno59b/pSlKrHK8BOZL8SOowvQP/n6hrdUspVL+Xx+4dmEmcb8Ispf+BQw27qPoxLtt2ltepcxOtfnvufe2zmaQDWLg9i3jPRqsSkxWNBw4gyprz7B35BNnKzPNi/3YfxA1uRm3WFNO9In4FK6RSlev0jv/76a2bPns27775L9+7dgfLOhE8++SSTJ09m8ODBlx3MjTfeSJcuXViwYEGVprdYLAQEBHAjg/DQXSHVVELT7j6YrnYIF/iybajaIYj6RKetqm6rUsbPyipyc3NdbvqtTMW5ImrBy+i9L/8JjvaiYpLHT6/VWNVSpbqmoKAggoODCQ4OZuTIkSQmJtKjRw+MRiNGo5EePXqwe/duRo0aVdvxCiGEEJdHhT4DKSkpPPTQQzRo0ABvb286duzIzp07z4WkKEyfPp2IiAi8vb3p27cvR44ccVpGVlYWw4YNw9/fn8DAQEaPHk1+fr7LxXG+KtXtVPVK3VU///xznaxHCCGEG6rjZoLs7Gx69epFnz59+O677wgJCeHIkSNOz9SZO3cuCxcu5NNPPyUmJoZp06bRv39/Dhw44OhcP2zYMM6cOUNCQgJlZWWMHDmSsWPHsmzZMhd+jLMqJQPDhw+vsRUKIYQQV7K/PvCuopb8r+bMmUNUVBSLFy92jIuJiXH8rSgKCxYs4MUXX2TQoEFA+ZuBw8LCWLVqFUOHDuXgwYOsWbOGHTt2OJrm3377bW6//XbeeOONavXV+zsudUktLi6u0ScCCiGEELWmhl5UFBUVRUBAgGOIj4+/6Oq++eYbunfvzr333ktoaChdu3blo48+cnx//PhxUlNT6du3r2NcQEAAPXr0YMuWLQBs2bKFwMBARyIA0LdvX/R6Pdu2bauBQilX7S6gBQUFTJ48mRUrVnD27NkLvrfZrozHUgohhHAzNdRMkJyc7NSB8GK1AgBJSUksWrSICRMm8MILL7Bjxw6eeuopvLy8GD58OKmpqQCEhYU5zRcWFub4LjU1ldBQ507EHh4eBAcHO6apCdVOBp577jl++uknFi1axMMPP8y7775LSkoKH3zwAa+99lqNBSaEEEJoUVUfeme32+nevTuzZ88GoGvXruzbt4/3339fc83v1W4m+Pbbb3nvvfe4++678fDw4Prrr+fFF19k9uzZLF26tDZiFEIIIVxXx3cTRERE0K5dO6dxbdu25eTJkwCEh4cDkJaW5jRNWlqa47vw8HDS051vebZarWRlZTmmqQnVTgaysrJo1qwZUJ4dZWWVP1L1uuuuY8OGDTUWmBBCCFGTKp5A6MpQHb169eLQoUNO4w4fPkyTJk2A8s6E4eHhrFu3zvG9xWJh27ZtxMbGAhAbG0tOTg67du1yTPPjjz9it9vp0aPHZZbEhaqdDDRr1ozjx48D0KZNG1asWAGU1xhUvLhICCGEcHfPPPMMW7duZfbs2Rw9epRly5bx4YcfEhcXB4BOp2P8+PG8+uqrfPPNN+zdu5dHHnmEyMhIxwP82rZty6233sqYMWPYvn07v/zyC+PGjWPo0KE1dicBXEafgZEjR/Lrr7/Su3dvnn/+eQYOHMg777xDWVkZ8+fPr7HAhBBCiBpVx88ZuPrqq1m5ciVTpkzh5ZdfJiYmhgULFjBs2DDHNM899xwFBQWMHTuWnJwcrrvuOtasWeP0Ar+lS5cybtw4br75ZvR6PXfffTcLFy504YdcqNqPI/6rEydOsGvXLlq0aEGnTp1qKq4qkccRi5omjyMW9Z4bP444es6rLj+O+OTkF+vl44hdfrtEkyZNHO0fQgghhFbpcPGthTUWifZUKRmoTnXEU089ddnBCCGEEKLuVSkZePPNN6u0MJ1OJ8mAuKJpsUq+wy513l3/d/Z11+C7XF1r8XQfWiunuoznMl825DR/PVWlZKDi7gEhhBDiilXHHQivJNq75BBCCCFEnXK5A6EQQghxRZCagUpJMiCEEMItXM5TBP86f30lzQRCCCGEm5OaASGEEO5BmgkqdVk1Axs3buShhx4iNjaWlJQUAD777DM2bdpUo8EJIYQQNUapgaGeqnYy8OWXX9K/f3+8vb3Zs2cPJSUlAOTm5jre2SyEEEKIK0e1k4FXX32V999/n48++ghPz3PvA+jVqxe7d++u0eCEEEKImlLXrzC+klS7z8ChQ4e44YYbLhgfEBBATk5OTcQkhBBC1Dx5AmGlql0zEB4eztGjRy8Yv2nTJpo1a1YjQQkhhBA1TvoMVKraycCYMWN4+umn2bZtGzqdjtOnT7N06VImTpzI448/XhsxCiGEEKIWVbuZ4Pnnn8dut3PzzTdTWFjIDTfcgNFoZOLEiTz55JO1EWOtGzgik3seTyc4xErSAW/ee7ERhxLNqsRy/7g0et2eS1SLEkqL9RzYaebjWRGcOnb57+CuKVoqpzseyWTAI2cJiyoF4MQhE0vfDGPnT+q/Y7yuykmxKaR/oJDzHVjPgkdDCBqoI+TR8peGAVjPKqQuVMjfCrY88LkKIp7TYYw+V92Z9ZVCzhqF4t/BXgBtf9Zh8Ku96tCHJpzh4WfTnMYlHzXyaO+2tbbOS+nQI597n8igZcdCGoRbmTGqKVvWBKgWD2hzH9fy8akq5KFDlat2zYBOp2Pq1KlkZWWxb98+tm7dSkZGBq+88kptxFfret+ZzdiXTrN0fjhx/VuRdMDErGVJBDQoUyWeTrEFfLukIePvaMmUoc0weCjM/jwJo7dNlXgqaK2cMs548snsCMbd2oonb2vFr7/4MmPxHzRpVaxKPBXqspwyPoWs/0Dkczpa/kdH+FM6Mv+pkPVF+feKonDiWYXSFIier6PFMh2eEfDH4wr2onNHNXsx+MXqCBlZd+2hf/xuYmiX9o5hwuCWdbbuizGZ7STtN/HOC41VjeN8WtzHtXp8qjJpJqjUZT+B0MvLi3bt2nHNNdfg6+t7WcuYMWMGOp3OaWjTps3lhnRZhozNZM2yYNYuD+bkERMLJzempEhH/wey6jSOClOHNSNhRTAnDptIOuDNvPHRhDUuo2WnIlXiqaC1ctqWEMCOH/05fdxISpKRJXMiKC7Q06ZbgSrxVKjLcir6VcHvRvC7XodXpI6Avjp8r4XC/eVHrNKTULQXIqfoMLfXYWyqI3KKDnsJ5Kw5t5yGD5YnAt4dazzEStlskJ3h6Rgs2eo+/2znT/58OjeCzSrXBpxPi/u4Vo9PwnXV/g/s06ePowryYn788cdqLa99+/b88MMP5wLyqLuDgoennZadCvninXPvsFcUHXs2+tGuW2GdxfF3fPzLM+68HINqMWi9nPR6hesH5mA02zm400e1OOq6nLw768j+SqHkhIKxiY6iwwoFiRDxTPn/p1Jeu4zO69w8Or0OnZdCYaJC8F3q9YxuFFPKsl37KC3Rc3CXD5/ER5Bx2uvSM7oprezjf6WF41O1uHp7YD2uGaj2mbdLly5On8vKykhMTGTfvn0MHz68+gF4eBAeHl6laUtKShwPOQKwWCzVXt/5/INtGDwgJ8O5GLIzPYhqUVLJXHVHp1N4bGYK+7abOXHIW7U4tFpOTdsUseDbo3gZ7RQV6Hl5dFNOHlGv7bKuyylkBNjz4cjdCugVsEPYEzoCby8/yRubgmc4pL2j0Ggq6Lzh7FKwpoE1s8bDqbLf9/jwxjPenDpmJDi0jIcmpDJv5RH+76Y2FBVcISeVOqK1ffx8Wjk+VYs8jrhS1U4G3nzzzYuOnzFjBvn5+dUO4MiRI0RGRmIymYiNjSU+Pp7o6OiLThsfH8/MmTOrvY4r1bjZKTRpU8yzg1uoHYomnTpm5IlbWmH2s3H9HblMfOskk4a00MzBsrblJpRX9zeepcPUDIoOQ+o8BY+Q8o6EOk8d0W9AyssKB/soYADfa8C3F6oe1M7vAHf8oDe/7zHz2bYD3DAwh++/aKBeYBqk5X1cjk/1S429tfChhx7ik08+qdY8PXr0YMmSJaxZs4ZFixZx/Phxrr/+evLy8i46/ZQpU8jNzXUMycnJLsVsyTJgs0JgiNVpfFBDK9kZ6rZhxs06RY9bLDx3T3Myz6hbfarVcrKW6Tn9h5Gje80sjo/g+AFvBj+aoVo8dV1OqW8phIzQEdhfh6mljqABOho8qCNj8bkzvXdbHS0+19P2Zx1tvtfR9B09thzwalTj4Vy2AosHp5KMRDZVvzZOa7S2j1fQ0vGpWqQDYaVqLBnYsmULJlP1stXbbruNe++9l06dOtG/f3/+97//kZOTw4oVKy46vdFoxN/f32lwhbVMz5HfzHS97lzyodMpdLkunwO71LllDhTiZp2i5625PHdvc9KSjSrFcY42y+lCOh14eqn331rX5aQUA39p9tfpuegBy+CnwyNIR8lJhaKD4NdbO09SM5ltRDYpJSvd89ITuzm193EtHp+qQx5HXLlqX64MGTLE6bOiKJw5c4adO3cybdo0l4IJDAykVatWF33CYW356sOGTFyQzOFfzRzaY+auMRmYzHbWfhFcZzGcb9zsFPrclc2MkTEU5esJCim/Ja0gz0BpcY3lbtWmtXIaOeUMO370IyPFC29fG33uyqFTz3ymPqjuUzDrspz8roeMTxS8wsHYHIp/h8ylCkGDzk2Tm6BgCAKvcCg+CmfeUPC/sfxWwgplmQrWs1D6Z0Vb8VHQmxU8w8EjoOaThjHTUtiaEED6KU8ahFt5+Nkz2Ozw86qgGl9XVZnMNiJjSh2fw6NKada+iLwcAxkp6lz5anEf1+rxSbiu2slAQIDzrTd6vZ7WrVvz8ssv069fP5eCyc/P59ixYzz88MMuLac61n8TREADG49MSiUoxErSfm+mDoshJ1Odq5SBI84C8MZXx5zGvzE+ioQV6px4QXvlFNjQyqSFJwkOtVKYZ+D4QRNTH2zG7g1+qsRToS7LKeI5HemLFE6/pmDNLn/oUPDdEDLm3Ancmgln3lSw/flQosABzt8DZH2pkPHhuc/HHy2//Gn0ko6gO2s8bBpGlDHl3T/wC7KRm+XB/u0+jB/Yitws9ZqcWnUu4vUvz/3PPTbzNABrlwcx75mL92GqbVrcx7V6fBKu0ymKUuWKD5vNxi+//ELHjh0JCnI9i584cSIDBw6kSZMmnD59mpdeeonExEQOHDhASEjIJee3WCwEBARwI4Pw0EkVo6ifOuzS3hXXvu4arC+t+qFMaIhVKeNnviY3N9flpt/KVJwrmk+ZjaGazdnnsxUXcyz+hVqNVS3VSsUNBgP9+vXj4MGDNZIMnDp1igceeICzZ88SEhLCddddx9atW6uUCAghhBDVIY8jrly16+U6dOhAUlISMTExLq/8iy++cHkZQgghhHBNtesfX331VSZOnMjq1as5c+YMFovFaRBCCCE0S24rvKgq1wy8/PLLPPvss9x+++0A3HnnnU6PJVYUBZ1Oh812hbywQgghhHuRJxBWqsrJwMyZM3nsscf46aefajMeIYQQQtSxKicDFTcd9O7du9aCEUIIIWqLdCCsXLU6EP7d2wqFEEIITZNmgkpVKxlo1arVJROCrCx13m8vhBBCiMtTrWRg5syZFzyBUAghhLgSSDNB5aqVDAwdOpTQ0NDaikUIIYSoPdJMUKkqP2dA+gsIIYQQ9VO17yYQQgghrkhSM1CpKicDdru9NuMQQgghapX0Gaiceu8MFUJUyb5u2kvE7zuYqnYIF1jRNlztEITWSc1ApbT3blQhhBBC1CmpGRBCCOEepGagUpIMCCGEcAvSZ6By0kwghBBCuDmpGRBCCOEepJmgUpIMCCGEcAvSTFA5aSYQQggh3JzUDAghhHAP0kxQKUkGhBBCuAdJBiolzQRCCCGEm5OaASGEEG5B9+fgyvz1lSQDQggh3IM0E1RKkgFg4IhM7nk8neAQK0kHvHnvxUYcSjSrEsv949LodXsuUS1KKC3Wc2CnmY9nRXDqmEmVeM6npXLSYkyy7cqVFejY95YvKT+YKMnSE9i2jK4vWAjuaHVMYzlm4Ld5fmTs8MJuA//mNnq+lY1PpJ2CFAP/7Rty0WXHvplN1K0ltRI3aGt/uuORTAY8cpawqFIAThwysfTNMHb+5K9KPOfTUjlVh9xaWDm37zPQ+85sxr50mqXzw4nr34qkAyZmLUsioEGZKvF0ii3g2yUNGX9HS6YMbYbBQ2H250kYvW2qxFNBa+WkxZhk25Xb+aI/aZu96DEnh35fZxLWq5T1o4IpTCs/3OSfNPDjsAb4xVi58dMs+q86S7vH8zEYy+f3DrcxcEO609B+XB4eZjvh15fWSsygvf0p44wnn8yOYNytrXjytlb8+osvMxb/QZNWxarEU0Fr5XSleO2119DpdIwfP94xrri4mLi4OBo0aICvry933303aWlpTvOdPHmSAQMGYDabCQ0NZdKkSVitVmqa6slASkoKDz30EA0aNMDb25uOHTuyc+fOOlv/kLGZrFkWzNrlwZw8YmLh5MaUFOno/0BWncVwvqnDmpGwIpgTh00kHfBm3vhowhqX0bJTkSrxVNBaOWkxJtl2YC2GUwkmOk3MJ+TqMvya2OgwLh/faBvHPi+/cty7wJeIG0roPCmfoHZWfKNtNLqpBFOD8lc16w3gHWJ3GlLWmYi6tRhPn9q7NNPa/rQtIYAdP/pz+riRlCQjS+ZEUFygp023AlXiqaC1cqoWpQaGy7Bjxw4++OADOnXq5DT+mWee4dtvv+Xf//4369ev5/Tp0wwZMsTxvc1mY8CAAZSWlrJ582Y+/fRTlixZwvTp0y8vkL+hajKQnZ1Nr1698PT05LvvvuPAgQPMmzePoKCgOlm/h6edlp0K2b3RzzFOUXTs2ehHu26FdRLDpfj4l19V5uUYVItBi+WkxZj+yh23nWLTodh0GIzOR02DSSFztxeKHc6sN+Lb1Mr6R4P4ulcIP9wfTMoPxkqXmbXfg5yDnsTcU3tJldb3J71eofegbIxmOwd3+qgWh9bLqUrqOBHIz89n2LBhfPTRR07nttzcXD7++GPmz5/PTTfdRLdu3Vi8eDGbN29m69atAKxdu5YDBw7wr3/9iy5dunDbbbfxyiuv8O6771JaWrO1ZKomA3PmzCEqKorFixdzzTXXEBMTQ79+/WjevPlFpy8pKcFisTgNrvAPtmHwgJwM564T2ZkeBIXUfDVMdel0Co/NTGHfdjMnDnmrFocWy0mLMZ3PXbedp49Cgy6lHFjkS1G6HrsNTnxj4myiJ8UZeorP6rEW6vn9Hz6EX1fCDf/IplHfEn55KpD07Z4XXebx/5jxb26lYdfaq4bW6v7UtE0Rq47sZfUfv/HUa6d4eXRTTh5Rrw+KVsuprv31PFRSUnk/lri4OAYMGEDfvn2dxu/atYuysjKn8W3atCE6OpotW7YAsGXLFjp27EhYWJhjmv79+2OxWNi/f3+N/iZVk4FvvvmG7t27c++99xIaGkrXrl356KOPKp0+Pj6egIAAxxAVFVWH0da9cbNTaNKmmPjHm6gdiqgmd952PebkggLf9g7ly85hHPmXmagBxeVHmz+vrhrdVELrEYUEtbXSdkwBkTeWcGz5hR3QrMVw8r8mYu6+Qq46a9ipY0aeuKUVTw1oyep/NmTiWyeJbqlun4ErWUUHQlcGgKioKKdzUXx8/EXX98UXX7B79+6Lfp+amoqXlxeBgYFO48PCwkhNTXVMc34iUPF9xXc1SdW7CZKSkli0aBETJkzghRdeYMeOHTz11FN4eXkxfPjwC6afMmUKEyZMcHy2WCwuJQSWLAM2KwT+JaMNamglO0PdGy3iZp2ixy0Wnr2rOZlnvFSNRYvlpMWYKrj7tvONttHnsyyshTrK8nV4h9rZ8kwAvo2teAXa0Xko+Dd3jsevmZXM3ReW1anvTdiKdTQZVLv9LrS6P1nL9Jz+o7wJ5eheM627FDL40QwWTlbnQkir5VRlNXRrYXJyMv7+5+7qMBovbOZKTk7m6aefJiEhAZNJ/TuKLkXVmgG73c5VV13F7Nmz6dq1K2PHjmXMmDG8//77F53eaDTi7+/vNLjCWqbnyG9mul6X5xin0yl0uS6fA7vUuk1GIW7WKXremstz9zYnLbnyttS6osVy0mJMsu2ceZgVvEPtlObqSP3FSOTNJRi8ILhDGXnHnU8c+X944BN54V0Xx780E9mnBFNw7d7Tpc396UI6HXh6qXd/25VSTrXtr+ehiyUDu3btIj09nauuugoPDw88PDxYv349CxcuxMPDg7CwMEpLS8nJyXGaLy0tjfDwcADCw8MvuLug4nPFNDVF1WQgIiKCdu3aOY1r27YtJ0+erLMYvvqwIbc9mEXfe7OIalHMk6+dwmS2s/aL4DqL4XzjZqdw05BsXotrQlG+nqCQMoJCyvAy2VWJp4LWykmLMcm2K5e6yYszG73IP2Ug9Rcvfh4RjF+MlZi7yq/uW48qIHmNiWMrvMk7YeDIUjOnfzbS/AHnpoC8EwYydnoSc0/dNBFobX8aOeUMHXrkE9a4lKZtihg55Qydeubz08q66WBdGa2VU3XUVDNBVdx8883s3buXxMREx9C9e3eGDRvm+NvT05N169Y55jl06BAnT54kNjYWgNjYWPbu3Ut6erpjmoSEBPz9/S84d7pK1XqdXr16cejQIadxhw8fpkmTumtnXf9NEAENbDwyKZWgECtJ+72ZOiyGnMyLd2aqbQNHnAXgja+OOY1/Y3wUCSvU+2fTWjlpMSbZduXK8vT89qYvRakGvALsNO5XTIfx+ej/XF3jW0q46iULv3/oQ+Jsf/xirPR8K4eQbs4dBI9/5Y053E54r9p7tsD5tLY/BTa0MmnhSYJDrRTmGTh+0MTUB5uxe4PfpWeuRVorp2qpwycQ+vn50aFDB6dxPj4+NGjQwDF+9OjRTJgwgeDgYPz9/XnyySeJjY3l2muvBaBfv360a9eOhx9+mLlz55KamsqLL75IXFzcRWsjXKFTFEW1OqcdO3bQs2dPZs6cyX333cf27dsZM2YMH374IcOGDbvk/BaLhYCAAG5kEB66K2BHFKKeuO9gzXZeqgkr2tZstamoG1aljJ/5mtzcXJebfitTca7oOHo2Bq/Lb7+3lRaz9+MXLjvWG2+8kS5durBgwQKg/KFDzz77LJ9//jklJSX079+f9957z6kJ4MSJEzz++OP8/PPP+Pj4MHz4cF577TU8PGr2Wl7VZABg9erVTJkyhSNHjhATE8OECRMYM2ZMleaVZEAIdUgyIGpKXSYDnUa5ngz89snlJwNapnr3zzvuuIM77rhD7TCEEELUd/KiokqpngwIIYQQdUKSgUqp/m4CIYQQQqhLagaEEEK4BXmFceUkGRBCCOEepJmgUtJMIIQQQrg5qRkQQgjhFnSKgs6Fu+ldmVfrJBkQQgjhHqSZoFLSTCCEEEK4OakZEEII4RbkboLKSTIghBDCPUgzQaWkmUAIIYRwc1IzIISoNi2+FOjZo/vVDuEC81q0VzsEcR5pJqicJANCCCHcgzQTVEqSASGEEG5BagYqJ30GhBBCCDcnNQNCCCHcgzQTVEqSASGEEG6jPlf1u0KaCYQQQgg3JzUDQggh3IOilA+uzF9PSTIghBDCLcjdBJWTZgIhhBDCzUnNgBBCCPcgdxNUSpIBIYQQbkFnLx9cmb++kmYCIYQQws1JzQAwcEQm9zyeTnCIlaQD3rz3YiMOJZpVieWORzIZ8MhZwqJKAThxyMTSN8PY+ZO/KvFoNab7x6XR6/ZcolqUUFqs58BOMx/PiuDUMZPEdBFa2sdrO6ZT283s+KghaftNFKR7cueik7S8Jc/xvaLA5rdC2Ls8iBKLgchuhfR9+QxBTUsd02x9ryFJP/mRcdCEwVNh3J7fL1jPic0+/PJmKJmHjXh622k/JJfrJqShr6Gjaoce+dz7RAYtOxbSINzKjFFN2bImoGYWfpm0vI9XiTQTVMrtawZ635nN2JdOs3R+OHH9W5F0wMSsZUkENChTJZ6MM558MjuCcbe24snbWvHrL77MWPwHTVoVqxKPVmPqFFvAt0saMv6OlkwZ2gyDh8Lsz5Mwetskpr/Q2j5e2zGVFekJaVvMzTPOXPT7HR82ZM+nDej78hke/DIJT287X45sgrVE55jGVqqj9W0WOj+YddFlpB80snJ0NDE35PPw10nc8dYpjq3zY8PrYS7HX8FktpO038Q7LzSusWW6Sqv7eFVV3E3gylBfqZoMNG3aFJ1Od8EQFxdXZzEMGZvJmmXBrF0ezMkjJhZObkxJkY7+D1z8IFDbtiUEsONHf04fN5KSZGTJnAiKC/S06VagSjxajWnqsGYkrAjmxGETSQe8mTc+mrDGZbTsVCQx/YXW9vHajimmdz7XTUinZb+8C75TFNi9JJgecRm0uCWPkDYl3PZGCvlpHhxN8HNM12t8Bt1GnaVh65KLruPQfwNo2KaE2CczCGpaSlSPQm54LpVf/xVMaX7NHFZ3/uTPp3Mj2KxybcD5tLqPV1nFcwZcGeopVZOBHTt2cObMGceQkJAAwL333lsn6/fwtNOyUyG7N547CCiKjj0b/WjXrbBOYvg7er1C70HZGM12Du70UTscQJsxAfj4l1+Z5OUYVI7kHC3EpMV9XM2YcpM9KcjwpEnPc4ms0c9OROciTu+pehOFrVSHh9G5N5mHScFaoidt3xVSZV4DtLCPi5qhap+BkJAQp8+vvfYazZs3p3fv3hedvqSkhJKSc5m6xWJxaf3+wTYMHpCT4VwM2ZkeRLW4+BVBXWjapogF3x7Fy2inqEDPy6ObcvKIugcYLcZUQadTeGxmCvu2mzlxyFvtcADtxKTFfVzNmAoyy9dpbmh1Gm9uaKUgo+qHw6bX57N7SQMOfutP69stFGR4sOWd8uNZfjWWcyXTyj5eHfLQocppps9AaWkp//rXvxg1ahQ6ne6i08THxxMQEOAYoqKi6jjKunHqmJEnbmnFUwNasvqfDZn41kmiW6rXPq/VmCqMm51CkzbFxD/eRO1QHLQYk6g5Ta8v4IbJafwwLZIF7drxyS0tiemdD4BOM0fV2nVF7uNKDQz1lGZ221WrVpGTk8OIESMqnWbKlCnk5uY6huTkZJfWackyYLNCYIjzVUJQQyvZKmb31jI9p/8wcnSvmcXxERw/4M3gRzNUi0erMQHEzTpFj1ssPHdPczLPeKkdDqCtmLS4j6sZk8+fNQKFmc7rKcz0wOcv8VxK99FnGbfnd8ZuOMwTO36nRd/ymsrAqNJLzHnl09I+LmqGZpKBjz/+mNtuu43IyMhKpzEajfj7+zsNrrCW6Tnym5mu153raKTTKXS5Lp8Du9S97ep8Oh14emkrJVU/JoW4WafoeWsuz93bnLRko4qxVNBeTFrcx9WMKSCqDJ+QMk5uPtffpSRPz5lfvYnsWv3+Cjod+IZZ8TQp/L46AL+IUkLba6PGrHZobx+vDrmboHKaaNw6ceIEP/zwA1999VWdr/urDxsycUEyh381c2iPmbvGZGAy21n7RXCdxwIwcsoZdvzoR0aKF96+NvrclUOnnvlMfbCZKvFoNaZxs1Poc1c2M0bGUJSvJyik/Ja0gjwDpcXq5LhajAm0t4/XdkylBXpyTpy7WrUke5F+wIQp0IZ/ZBlXjchi63shBDYtJSCqlF/eDMU3zEqL855FYDntSXGOgbzTntjtkH6gvH9MYJNSvHzKOw7u+KgBTW/IR6eDI2v92f5BQ+5YeAp9DfWlM5ltRMacq2UIjyqlWfsi8nIMZKSoczWu1X28yuSthZXSRDKwePFiQkNDGTBgQJ2ve/03QQQ0sPHIpFSCQqwk7fdm6rAYcjI96zwWgMCGViYtPElwqJXCPAPHD5qY+mAzdm/wu/TMbhTTwBFnAXjjq2NO498YH0XCCnVOclqMCbS3j9d2TGl7Tax4KMbx+efZ4QC0H5LNrXNPc/XYTMqKdCS8GEGJxUCj7oUM+eQEHsZzB/rNC0LY/1WQ4/NndzYH4L5/HSfq2vIahOPrfdn2Xgi2Uh0hbYoZ/H6yo99ATWjVuYjXvzy3Lz028zQAa5cHMe+Z6BpbT3VodR8XrtMpirqpjt1uJyYmhgceeIDXXnutWvNaLBYCAgK4kUF46NQ7sAkh1Pfs0f1qh3CBeS3aqx2C5lmVMn7ma3Jzc11u+q1Mxbki9raX8fC8/LugrGXFbPlueq3GqhbVawZ++OEHTp48yahRo9QORQghRH0mjyOulOrJQL9+/VC5ckIIIYRwa6onA0IIIURdkIcOVU6SASGEEO7BrpQPrsxfT0kyIIQQwj1In4FKXQE3hgohhBCiNknNgBBCCLegw8U+AzUWifZIMiCEEMI9yBMIKyXNBEIIIYSbk5oBIYQQbkFuLaycJANCCCHcg9xNUClpJhBCCCHcnNQMCCGEcAs6RUHnQidAV+bVOkkGhBD1ghbfEDjy0Am1Q7jA4tZN1A5BPfY/B1fmr6ekmUAIIYRwc1IzIIQQwi1IM0HlJBkQQgjhHuRugkpJMiCEEMI9yBMIKyV9BoQQQohaEB8fz9VXX42fnx+hoaEMHjyYQ4cOOU1TXFxMXFwcDRo0wNfXl7vvvpu0tDSnaU6ePMmAAQMwm82EhoYyadIkrFZrjcYqyYAQQgi3UPEEQleG6li/fj1xcXFs3bqVhIQEysrK6NevHwUFBY5pnnnmGb799lv+/e9/s379ek6fPs2QIUMc39tsNgYMGEBpaSmbN2/m008/ZcmSJUyfPr2migWQZgIhhBDuoo6bCdasWeP0ecmSJYSGhrJr1y5uuOEGcnNz+fjjj1m2bBk33XQTAIsXL6Zt27Zs3bqVa6+9lrVr13LgwAF++OEHwsLC6NKlC6+88gqTJ09mxowZeHl5Xf7vOY/UDAghhBDVYLFYnIaSkpIqzZebmwtAcHAwALt27aKsrIy+ffs6pmnTpg3R0dFs2bIFgC1bttCxY0fCwsIc0/Tv3x+LxcL+/ftr6idJMiCEEMI96OyuDwBRUVEEBAQ4hvj4+Euu2263M378eHr16kWHDh0ASE1NxcvLi8DAQKdpw8LCSE1NdUxzfiJQ8X3FdzVFmgmEEEK4hxpqJkhOTsbf398x2mg0XnLWuLg49u3bx6ZNmy5//bVIagaEEEKIavD393caLpUMjBs3jtWrV/PTTz/RuHFjx/jw8HBKS0vJyclxmj4tLY3w8HDHNH+9u6Dic8U0NUGSASGEEO5BqYGhOqtTFMaNG8fKlSv58ccfiYmJcfq+W7dueHp6sm7dOse4Q4cOcfLkSWJjYwGIjY1l7969pKenO6ZJSEjA39+fdu3aVS+gv+H2zQQdeuRz7xMZtOxYSINwKzNGNWXLmgDV4rnjkUwGPHKWsKhSAE4cMrH0zTB2/uR/iTlrl9bK6f5xafS6PZeoFiWUFus5sNPMx7MiOHXMJDH9hda23V/dNy6N0S+ksvKjhrz/UiNVYlDj/64sX8futwI58YOZ4rN6gtuV0uOFbEI6lcdQVqBj57xATv5gpiRHj29jK+0ezqPNA/mOZXz3cBip2533r9b359Hz5axai/t8Wth21VHXjyOOi4tj2bJlfP311/j5+Tna+AMCAvD29iYgIIDRo0czYcIEgoOD8ff358knnyQ2NpZrr70WgH79+tGuXTsefvhh5s6dS2pqKi+++CJxcXFVap6oKrdPBkxmO0n7TXz/eTAvffKH2uGQccaTT2ZHkHLciE4Ht9ybxYzFfxDXrxUnDqt3UtFaOXWKLeDbJQ05nGjG4KEw4vkzzP48iTG9W1NSZJCYzqO1bXe+Vp0LGfBQFkn71U2Y1Pi/2/RiA3KOeHLD3EzMoTaOfePD9yPDuOt/p/EJs7H9tSDObDVxw+uZ+DaycvoXb7bMDMYcaiP65iLHclrdl0fXp3Icnz286+YpeVrZdlq2aNEiAG688Uan8YsXL2bEiBEAvPnmm+j1eu6++25KSkro378/7733nmNag8HA6tWrefzxx4mNjcXHx4fhw4fz8ssv12isqiYDNpuNGTNm8K9//YvU1FQiIyMZMWIEL774Ijqdrk5i2PmTv+pX3efbluB8xbZkTgR3PHKWNt0KVE0GtFZOU4c1c/o8b3w0K/btp2WnIvZt85WYzqO1bVfBZLYx+Z0TLJjUmAeeTrv0DLWorv/vrMU6Tqw1c/N7GYRfXX5bWtcnc0n+yZvfl/nR7Zkc0vcYaTG4gIge5d+3vj+fQ8t9yfjN6JQMeJgUzCF1+25dLW27aqnj5wwoVZjeZDLx7rvv8u6771Y6TZMmTfjf//5XrXVXl6p9BubMmcOiRYt45513OHjwIHPmzGHu3Lm8/fbbaoalGXq9Qu9B2RjNdg7u9FE7HE3z8bcBkJej3hX4X2kxJi0ZNzuF7ev82bPRT+1QnNTF/51iBcWmw2B0PlkYjArpu8urfkO7lpD8ozcFaQYUBc5sNZJ73JNG1xU5zXPsWx+W9WjMyjsi2DkvEGtR7V9IaXXbXZIC2F0Y6u+rCdStGdi8eTODBg1iwIABADRt2pTPP/+c7du3X3T6kpISp4c7WCyWOomzrjVtU8SCb4/iZbRTVKDn5dFNOXlEquIqo9MpPDYzhX3bzZw45K12OIA2Y9KS3oOyadGxiCdvb6l2KA51+X/n6asQ0rWYX98LILBZGaaGNo6v9iEj0YhfdPkz56+dlsUv0xqw4obG6DwUdDro9epZR00CQLM7CvCNtOIdaiP7kBc73wgk97gnN7+TUStxgza3XVXJK4wrp2oy0LNnTz788EMOHz5Mq1at+PXXX9m0aRPz58+/6PTx8fHMnDmzjqOse6eOGXnillaY/Wxcf0cuE986yaQhLSQhqMS42Sk0aVPMs4NbqB2KgxZj0oqQyFIef/k0U4Y2o6xEOzc01fX/3Q1zz7LphQYsv6ExOoNCg3alxAwo4Oz+8pqBA5/5k5Fo5OZF6fhGWkndaXL0GYjsWQyUNx1UCG5dhneIje9HhGE56YF/dM2+yAa0u+2E61RNBp5//nksFgtt2rTBYDBgs9mYNWsWw4YNu+j0U6ZMYcKECY7PFouFqKiougq3zljL9Jz+o/yAcHSvmdZdChn8aAYLJ9e/3+qquFmn6HGLhWfvak7mmZp5RrertBiTlrToVERQiJV3vz/sGGfwgI7XFnDnyEzuaNoJu71u+gydr67/7/yjrdz+rzTKCnWU5esxh9r4aXxD/KLKsBbr2P1mIDe9k0HUjeXNAsFtysg66Mm+j/0dycBfhXQurzXIO1E7yYBWt12VKbjYZ6DGItEcVZOBFStWsHTpUpYtW0b79u1JTExk/PjxREZGMnz48AumNxqNNXorxZVCpwNPr3q8F14WhbhZKfS8NZdJ97QgLVkL+4UWY9KexI2+jO3Tymncs28mk3zUxIp3QzRzMqmr/ztPs4Kn2UZJrp7Tm7zpPikbuxXsZTp0f3lNns7w9+eyrIPlyad3iK1WYr1Stl2l6rgD4ZVE1WRg0qRJPP/88wwdOhSAjh07cuLECeLj4y+aDNQGk9lGZEyp43N4VCnN2heRl2MgI6Xur+pGTjnDjh/9yEjxwtvXRp+7cujUM5+pDza79My1SGvlNG52Cn3uymbGyBiK8vUEhZQBUJBnoLRYnepLLcYE2tt2RQWGC/pRFBfqycu+cHxdUeP/LmWjCUWBgBgrlpMe7JwbRECzMloOyUfvCeHXFLPj9SAMpix8I22k7jBybJUP1zyfDYDlpAdJ3/rQuHcRxsDyPgPb44MIu7qY4DZltRKzFredqBmqJgOFhYXo9c4HSYPBgN1ed7fJtOpcxOtfHnN8fmzmaQDWLg9i3jPRdRZHhcCGViYtPElwqJXCPAPHD5qY+mAzdm9Qt9eu1spp4IizALzx1TGn8W+MjyJhRXCdxwPajAm0t+20SI3/u9I8PbvmB1KQ6oEx0EaTfoV0eyYHvWf5973nZ7BrfhAbJjakJFePb6SNq57JofWfDx3Seyqc3mLiwD/9sBbqMUdYadKvkM5P5NZazFc8O+BK5UXd3sFZp3RKVW6ErCUjRozghx9+4IMPPqB9+/bs2bOHsWPHMmrUKObMmXPJ+S0WCwEBAdzIIDx0nnUQsRBCVN3IQyfUDuECi1s3UTsEJ1aljJ/5mtzcXKeX/9SkinPFzR2ew8Nw+c13VlsJ6/bNrdVY1aJqzcDbb7/NtGnTeOKJJ0hPTycyMpL/+7//Y/r06WqGJYQQQrgVVZMBPz8/FixYwIIFC9QMQwghhDuQDoSVcvt3EwghhHATkgxUSp4aIYQQQrg5qRkQQgjhHqRmoFKSDAghhHAPcmthpSQZEEII4RbkRUWVkz4DQgghhJuTmgEhhBDuQfoMVEqSASGEEO7BroDOhRO6vf4mA9JMIIQQQrg5qRkQQgjhHqSZoFKSDAghhHATLiYDSDIghBDapnPlBvLaobU3BAL03ZendghOivOt/NxD7SiEJANCCCHcgzQTVEqSASGEEO7BruBSVb/cTSCEEEKI+kpqBoQQQrgHxV4+uDJ/PSXJgBBCCPcgfQYqJcmAEEII9yB9BiolfQaEEEIINyc1A0IIIdyDNBNUSpIBIYQQ7kHBxWSgxiLRHGkmEEIIIdyc1AwIIYRwD9JMUClJBoQQQrgHux1w4VkBdnnOQL3VoUc+9z6RQcuOhTQItzJjVFO2rAlQLZ77x6XR6/ZcolqUUFqs58BOMx/PiuDUMZNqMYH2yqnCwBGZ3PN4OsEhVpIOePPei404lGhWJZY7HslkwCNnCYsqBeDEIRNL3wxj50/+qsRTQbbdpT004QwPP5vmNC75qJFHe7dVJR5QZ7tZC+DY20Yy1nlQmqXDr42dVs8XE9Cx/CR47F0v0tZ4UJyqR+8J/u1sNH+qhIBO506SlgN6js43YtlvQKeH0FvKaPlcCR7qbFpRRW7fZ8BktpO038Q7LzRWOxQAOsUW8O2Shoy/oyVThjbD4KEw+/MkjN42VePSWjkB9L4zm7EvnWbp/HDi+rci6YCJWcuSCGhQpko8GWc8+WR2BONubcWTt7Xi1198mbH4D5q0KlYlngqy7armj99NDO3S3jFMGNxStVhAne12cLqJrC0G2scXc+3KAoJ7Wtk9xkxxWvkbIX2a2mn9QgnXflVA938WYoq0s3usmdKs8u9L0nXsftSMd7Sdq5cV0OX9QvKPGjgwVd2LGYeKZgJXhnpK1ZqBvLw8pk2bxsqVK0lPT6dr16689dZbXH311XUWw86f/FW/cjvf1GHNnD7PGx/Nin37admpiH3bfFWKSnvlBDBkbCZrlgWzdnkwAAsnN+aamy30fyCLFe+E1Xk82xKcr9qWzIngjkfO0qZbAScOq3cwlG1XNTYbZGd4qrLui6nr7WYrhvQfPOi8sIig7uUXH83jSslc78Gp5Z60eKqU8AHW8+ZQaPVcCae/8iL/sJ7ga21krPdA76HQ5sUSdPryadpOL2brEB8KT5Zgjlb5ZCp9Biqlas3Ao48+SkJCAp999hl79+6lX79+9O3bl5SUFDXD0hQf//J/yrwcg8qRaIuHp52WnQrZvdHPMU5RdOzZ6Ee7boUqRlZOr1foPSgbo9nOwZ0+aoejKVrddo1iSlm2ax9LNh9g8tsnCIksVS0WNSg2UGw69Ebn8XqjQs7uC48/9jJI+bcnHn4Kvq3LmwnspaDz5M9E4M/5TeUn0IstQ2iHajUDRUVFfPnll3z99dfccMMNAMyYMYNvv/2WRYsW8eqrr14wT0lJCSUlJY7PFoulzuJVg06n8NjMFPZtN3PikLfa4WiKf7ANgwfkZDjvwtmZHkS1KKlkrtrXtE0RC749ipfRTlGBnpdHN+XkEY1UkWqEFrfd73t8eOMZb04dMxIcWsZDE1KZt/II/3dTG4oK3OMk5uEDAZ1tJL3vhU+zYrwaKKT+z4PcXw1OV/QZPxvYN8kbWzEYQxS6fliIV1D598E9bBx5Xccfn3gS/XAZtkI4+mZ5dlGSoYFWaXkccaVU2zpWqxWbzYbJ5Hyg9Pb2ZtOmTRedJz4+noCAAMcQFRVVF6GqZtzsFJq0KSb+8SZqhyKq6NQxI0/c0oqnBrRk9T8bMvGtk0S3VLfPgLi0nT/5s3F1IMcPerNrvT8vPtwMX38bNwzMUTu0OtU+vgiAjTf58uNVviQv9SL8Nivozp0Eg6+x0ePLAq7+VyENelnZO9Gb0rPlfQZ8W9hpP6uYk5968VN3Xzbc6It3IwWvBnan2gK1KIrd5aG+Uq1mwM/Pj9jYWF555RXatm1LWFgYn3/+OVu2bKFFixYXnWfKlClMmDDB8dlisdTbhCBu1il63GLh2buak3nGS+1wNMeSZcBmhcAQq9P4oIZWsjPU6wpjLdNz+o/yK6Gje8207lLI4EczWDi5fu6nl0Or2+58BRYPTiUZiWyqXi2TGszRCt2XFGErBGuBDmOIwt5nTXg3PpcMGMzl0xGtENC5hF9u9yDlK09ixpQ3q4QPsBI+wEpJpg6DWUEHnPinJ96NNXAiVRTXru6lz0Dt+Oyzz1AUhUaNGmE0Glm4cCEPPPAAev3FwzIajfj7+zsN9Y9C3KxT9Lw1l+fubU5asvHSs7gha5meI7+Z6XpdnmOcTqfQ5bp8DuzSzj1MOh14etXfA8jluBK2nclsI7JJKVnp2ulQWJcM5vImgLJcOLvZg5CbrJVPbC/vK/BXxoYKHmZIXeOB3gjBsX+zDKE6VdPw5s2bs379egoKCrBYLERERHD//ffTrFmzS89cQ0xmG5Ex5/bk8KhSmrUvIi/HQEZK3V+Rj5udQp+7spkxMoaifD1BIeW3WhXkGSgtVi9301o5AXz1YUMmLkjm8K9mDu0xc9eYDExmO2u/CFYlnpFTzrDjRz8yUrzw9rXR564cOvXMZ+qDdbc/X4xsu0sbMy2FrQkBpJ/ypEG4lYefPYPNDj+vClIlHlBnu539xYCilN9CWHhSz5F5RswxdiIHl7f/H//Qi5A+VrxCFMqydSR/7kVJuo6w/udO9MnLPAnoYsNgVsja4sGReUZajC/BUwvXboqLfQbqcc2AJurkfHx88PHxITs7m++//565c+fW2bpbdS7i9S+POT4/NvM0AGuXBzHvmeg6i6PCwBFnAXjjq2NO498YH0XCCnUOlKC9cgJY/00QAQ1sPDIplaAQK0n7vZk6LIacTHWu5gIbWpm08CTBoVYK8wwcP2hi6oPN2L3B79Iz1yLZdpfWMKKMKe/+gV+QjdwsD/Zv92H8wFbkZql3iFRju1nzdBxdYKQ4TYdngELoLVZaPFWC3hNsdig4rufMN96UZuvwDFTw72Cj26eF+LY41wSQu9dA0rtGrIXgE2On7fRiIu7USK2A3Q46F5or6nGfAZ2iqJfqfP/99yiKQuvWrTl69CiTJk3CZDKxceNGPD0vfVCwWCwEBARwI4Pw0LlndZ4Q4k86ndoRXEiDV5J99+VdeqI6VJxvZUaPdeTm5tZa02/FueJmv2F46C6/VsWqlLIub2mtxqoWVWsGcnNzmTJlCqdOnSI4OJi7776bWbNmVSkREEIIIapFmgkqpWoycN9993HfffepGYIQQgg3odjtKC40E9TnWws1cOenEEIIIdSkiQ6EQgghRK2TZoJKSTIghBDCPdgVp6cpVls9TgakmUAIIYRwc1IzIIQQwj0oCuDKcwbqb82AJANCCCHcgmJXUFxoJlDxsTy1TpIBIYQQ7kGx41rNgNxaKIQQQojL8O6779K0aVNMJhM9evRg+/btaod0AUkGhBBCuAXFrrg8VNfy5cuZMGECL730Ert376Zz587079+f9PT0WviFl0+SASGEEO5Bsbs+VNP8+fMZM2YMI0eOpF27drz//vuYzWY++eSTWviBl++K7jNQ0ZnDSplLz5EQQtQH8qKiqijO18gbBP9UEU9ddM5z9VxhpfyV8haLxWm80WjEaDReMH1paSm7du1iypQpjnF6vZ6+ffuyZcuWyw+kFlzRyUBeXvnbtzbxP5UjEUKoTnvnXU36uYfaEVxcXl4eAQEBtbJsLy8vwsPD2ZTq+rnC19eXqKgop3EvvfQSM2bMuGDazMxMbDYbYWFhTuPDwsL4/fffXY6lJl3RyUBkZCTJycn4+fmhc/H1pRaLhaioKJKTkzXzakqJqWq0FpPW4gGJqaokpqqpyZgURSEvL4/IyMgaiu5CJpOJ48ePU1pa6vKyFEW54HxzsVqBK80VnQzo9XoaN25co8v09/fXzD9cBYmparQWk9biAYmpqiSmqqmpmGqrRuB8JpMJk8lU6+s5X8OGDTEYDKSlpTmNT0tLIzw8vE5juRTpQCiEEELUAi8vL7p168a6desc4+x2O+vWrSM2NlbFyC50RdcMCCGEEFo2YcIEhg8fTvfu3bnmmmtYsGABBQUFjBw5Uu3QnEgy8Cej0chLL72kqbYfialqtBaT1uIBiamqJKaq0WJMWnX//feTkZHB9OnTSU1NpUuXLqxZs+aCToVq0yn1+WHLQgghhLgk6TMghBBCuDlJBoQQQgg3J8mAEEII4eYkGRBCCCHcnCQDaO/1khs2bGDgwIFERkai0+lYtWqVqvHEx8dz9dVX4+fnR2hoKIMHD+bQoUOqxrRo0SI6derkeOhJbGws3333naox/dVrr72GTqdj/PjxqsUwY8YMdDqd09CmTRvV4qmQkpLCQw89RIMGDfD29qZjx47s3LlTtXiaNm16QTnpdDri4uJUi8lmszFt2jRiYmLw9vamefPmvPLKK3XyDP+/k5eXx/jx42nSpAne3t707NmTHTt2qBqTcJ3bJwNafL1kQUEBnTt35t1331UthvOtX7+euLg4tm7dSkJCAmVlZfTr14+CggLVYmrcuDGvvfYau3btYufOndx0000MGjSI/fv3qxbT+Xbs2MEHH3xAp06d1A6F9u3bc+bMGcewadMmVePJzs6mV69eeHp68t1333HgwAHmzZtHUFCQajHt2LHDqYwSEhIAuPfee1WLac6cOSxatIh33nmHgwcPMmfOHObOncvbb7+tWkwAjz76KAkJCXz22Wfs3buXfv360bdvX1JSUlSNS7hIcXPXXHONEhcX5/hss9mUyMhIJT4+XsWozgGUlStXqh2Gk/T0dAVQ1q9fr3YoToKCgpR//OMfaoeh5OXlKS1btlQSEhKU3r17K08//bRqsbz00ktK586dVVv/xUyePFm57rrr1A7jbz399NNK8+bNFbvdrloMAwYMUEaNGuU0bsiQIcqwYcNUikhRCgsLFYPBoKxevdpp/FVXXaVMnTpVpahETXDrmoGK10v27dvXMU6rr5fUktzcXACCg4NVjqSczWbjiy++oKCgQBOP+IyLi2PAgAFO+5Wajhw5QmRkJM2aNWPYsGGcPHlS1Xi++eYbunfvzr333ktoaChdu3blo48+UjWm85WWlvKvf/2LUaNGufwCNFf07NmTdevWcfjwYQB+/fVXNm3axG233aZaTFarFZvNdsEz/r29vVWvcRKucesnEF5Jr5fUCrvdzvjx4+nVqxcdOnRQNZa9e/cSGxtLcXExvr6+rFy5knbt2qka0xdffMHu3bs104bao0cPlixZQuvWrTlz5gwzZ87k+uuvZ9++ffj5+akSU1JSEosWLWLChAm88MIL7Nixg6eeegovLy+GDx+uSkznW7VqFTk5OYwYMULVOJ5//nksFgtt2rTBYDBgs9mYNWsWw4YNUy0mPz8/YmNjeeWVV2jbti1hYWF8/vnnbNmyhRYtWqgWl3CdWycDovri4uLYt2+fJq4CWrduTWJiIrm5ufznP/9h+PDhrF+/XrWEIDk5maeffpqEhIQ6fztaZc6/iuzUqRM9evSgSZMmrFixgtGjR6sSk91up3v37syePRuArl27sm/fPt5//31NJAMff/wxt912W62+UrcqVqxYwdKlS1m2bBnt27cnMTGR8ePHExkZqWo5ffbZZ4waNYpGjRphMBi46qqreOCBB9i1a5dqMQnXuXUycCW9XlILxo0bx+rVq9mwYUONvzr6cnh5eTmuRrp168aOHTt46623+OCDD1SJZ9euXaSnp3PVVVc5xtlsNjZs2MA777xDSUkJBoNBldgqBAYG0qpVK44ePapaDBERERckbG3btuXLL79UKaJzTpw4wQ8//MBXX32ldihMmjSJ559/nqFDhwLQsWNHTpw4QXx8vKrJQPPmzVm/fj0FBQVYLBYiIiK4//77adasmWoxCde5dZ+BK+n1kmpSFIVx48axcuVKfvzxR2JiYtQO6aLsdjslJSWqrf/mm29m7969JCYmOobu3bszbNgwEhMTVU8EAPLz8zl27BgRERGqxdCrV68Lbk09fPgwTZo0USmicxYvXkxoaCgDBgxQOxQKCwvR650P0QaDAbvdrlJEznx8fIiIiCA7O5vvv/+eQYMGqR2ScIFb1wyANl8vmZ+f73Tldvz4cRITEwkODiY6OrrO44mLi2PZsmV8/fXX+Pn5kZqaCkBAQADe3t51Hg/AlClTuO2224iOjiYvL49ly5bx888/8/3336sSD5S3p/61H4WPjw8NGjRQrX/FxIkTGThwIE2aNOH06dO89NJLGAwGHnjgAVXiAXjmmWfo2bMns2fP5r777mP79u18+OGHfPjhh6rFBOXJ5OLFixk+fDgeHuofGgcOHMisWbOIjo6mffv27Nmzh/nz5zNq1ChV4/r+++9RFIXWrVtz9OhRJk2aRJs2bTT3Sl5RTWrfzqAFb7/9thIdHa14eXkp11xzjbJ161ZV4/npp58U4IJh+PDhqsRzsVgAZfHixarEoyiKMmrUKKVJkyaKl5eXEhISotx8883K2rVrVYunMmrfWnj//fcrERERipeXl9KoUSPl/vvvV44ePapaPBW+/fZbpUOHDorRaFTatGmjfPjhh2qHpHz//fcKoBw6dEjtUBRFURSLxaI8/fTTSnR0tGIymZRmzZopU6dOVUpKSlSNa/ny5UqzZs0ULy8vJTw8XImLi1NycnJUjUm4Tl5hLIQQQrg5t+4zIIQQQghJBoQQQgi3J8mAEEII4eYkGRBCCCHcnCQDQgghhJuTZEAIIYRwc5IMCCGEEG5OkgEhhBDCzUkyIISLRowYweDBgx2fb7zxRsaPH1/ncfz888/odDpycnIqnUan07Fq1aoqL3PGjBl06dLFpbj++OMPdDodiYmJLi1HCFF7JBkQ9dKIESPQ6XTodDrH2w1ffvllrFZrra/7q6++4pVXXqnStFU5gQshRG1T/20cQtSSW2+9lcWLF1NSUsL//vc/4uLi8PT0ZMqUKRdMW1paipeXV42sNzg4uEaWI4QQdUVqBkS9ZTQaCQ8Pp0mTJjz++OP07duXb775BjhXtT9r1iwiIyNp3bo1AMnJydx3330EBgYSHBzMoEGD+OOPPxzLtNlsTJgwgcDAQBo0aMBzzz3HX1/v8ddmgpKSEiZPnkxUVBRGo5EWLVrw8ccf88cff9CnTx8AgoKC0Ol0jBgxAih/g158fDwxMTF4e3vTuXNn/vOf/zit53//+x+tWrXC29ubPn36OMVZVZMnT6ZVq1aYzWaaNWvGtGnTKCsru2C6Dz74gKioKMxmM/fddx+5ublO3//jH/+gbdu2mEwm2rRpw3vvvVftWIQQ6pFkQLgNb29vSktLHZ/XrVvHoUOHSEhIYPXq1ZSVldG/f3/8/PzYuHEjv/zyC76+vtx6662O+ebNm8eSJUv45JNP2LRpE1lZWaxcufJv1/vII4/w+eefs3DhQg4ePMgHH3yAr68vUVFRfPnllwAcOnSIM2fO8NZbbwEQHx/PP//5T95//33279/PM888w0MPPcT69euB8qRlyJAhDBw4kMTERB599FGef/75apeJn58fS5Ys4cCBA7z11lt89NFHvPnmm07THD16lBUrVvDtt9+yZs0a9uzZwxNPPOH4funSpUyfPp1Zs2Zx8OBBZs+ezbRp0/j000+rHY8QQiUqvzVRiFoxfPhwZdCgQYqiKIrdblcSEhIUo9GoTJw40fF9WFiY0+tgP/vsM6V169aK3W53jCspKVG8vb2V77//XlEURYmIiFDmzp3r+L6srExp3LixY12K4vza4kOHDimAkpCQcNE4K15XnZ2d7RhXXFysmM1mZfPmzU7Tjh49WnnggQcURVGUKVOmKO3atXP6fvLkyRcs668AZeXKlZV+//rrryvdunVzfH7ppZcUg8GgnDp1yjHuu+++U/R6vXLmzBlFURSlefPmyrJly5yW88orryixsbGKoijK8ePHFUDZs2dPpesVQqhL+gyIemv16tX4+vpSVlaG3W7nwQcfZMaMGY7vO3bs6NRP4Ndff+Xo0aP4+fk5Lae4uJhjx46Rm5vLmTNn6NGjh+M7Dw8PunfvfkFTQYXExEQMBgO9e/euctxHjx6lsLCQW265xWl8aWkpXbt2BeDgwYNOcQDExsZWeR0Vli9fzsKFCzl27Bj5+flYrVb8/f2dpomOjqZRo0ZO67Hb7Rw6dAg/Pz+OHTvG6NGjGTNmjGMaq9VKQEBAteMRQqhDkgFRb/Xp04dFixbh5eVFZGQkHh7Ou7uPj4/T5/z8fLp168bSpUsvWFZISMhlxeDt7V3tefLz8wH473//63QShvJ+EDVly5YtDBs2jJkzZ9K/f38CAgL44osvmDdvXrVj/eijjy5ITgwGQ43FKoSoXZIMiHrLx8eHFi1aVHn6q666iuXLlxMaGnrB1XGFiIgItm3bxg033ACUXwHv2rWLq6666qLTd+zYEbvdzvr16+nbt+8F31fUTNhsNse4du3aYTQaOXnyZKU1Cm3btnV0hqywdevWS//I82zevJkmTZowdepUx7gTJ05cMN3Jkyc5ffo0kZGRjvXo9Xpat25NWFgYkZGRJCUlMWzYsGqtXwihHdKBUIg/DRs2jIYNGzJo0CA2btzI8ePH+fnnn3nqqac4deoUAE8//TSvvfYaq1at4vfff+eJJ57422cENG3alOHDhzNq1ChWrVrlWOaKFSsAaNKkCTqdjtWrV5ORkUF+fj5+fn5MnDiRZ555hk8//ZRjx46xe/du3n77bUenvMcee4wjR44wadIkDh06xLJly1iyZEm1fm/Lli05efIkX3zxBceOHWPhwoUX7QxpMpkYPnw4v/76Kxs3buSpp57ivvvuIzw8HICZM2cSHx/PwoULOXz4MHv37mXx4sXMnz+/WvEIIdQjyYAQfzKbzWzYsIHo6GiGDBlC27ZtGT16NMXFxY6agmeffZaHH36Y4cOHExsbi5+fH3fdddffLnfRokXcc889PPHEE7Rp04YxY8ZQUFAAQKNGjZg5cybPP/88YWFhjBs3DoBXXnmFadOmER8fT9u2bbn11lv573//S0xMDFDejv/ll1+yatUqOnfuzPvvv8/s2bOr9XvvvPNOnnnmGcaNG0eXLl3YvHkz06ZNu2C6Fi1aMGTIEG6//Xb69etHp06dnG4dfPTRR/nHP/7B4sWL6dixI71792bJkiWOWIUQ2qdTKuv5JIQQQgi3IDUDQgghhJuTZEAIIYRwc5IMCCGEEG5OkgEhhBDCzUkyIIQQQrg5SQaEEEIINyfJgBBCCOHmJBkQQggh3JwkA0IIIYSbk2RACCGEcHOSDAghhBBu7v8BeW/NuJPs2zgAAAAASUVORK5CYII=", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], + "source": [ + "# Получение истинных и предсказанных меток для всех тестовых данных\n", + "true_labels = np.argmax(y_test, axis=1)\n", + "\n", + "predicted_labels = np.argmax(model.predict(X_test), axis=1)\n", + "\n", + "# Вывод подробного отчета о качестве классификации\n", + "print(classification_report(true_labels, predicted_labels))\n", + "# Построение и визуализация матрицы ошибок\n", + "conf_matrix = confusion_matrix(true_labels, predicted_labels)\n", + "\n", + "display = ConfusionMatrixDisplay(confusion_matrix=conf_matrix)\n", + "display.plot()\n", + "plt.show()" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "amaspXGW1EVy" + }, + "source": [ + "### 9) Тестирование на собственных изображениях\n", + "\n", + "Загружаем и обрабатываем собственные изображения цифр, созданные ранее, и проверяем способность модели их корректно распознавать." + ] + }, + { + "cell_type": "code", + "execution_count": 10, + "metadata": { + "id": "ktWEeqWd1EyF" + }, + "outputs": [ + { + "data": { + "image/png": "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", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 45ms/step\n", + "I think it's 2\n" + ] + }, + { + "data": { + "image/png": "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", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 46ms/step\n", + "I think it's 7\n" + ] + } + ], + "source": [ + "# Загрузка и обработка собственных изображений\n", + "from PIL import Image\n", + "\n", + "for name_image in ['2.png', '7.png']:\n", + " file_data = Image.open(name_image)\n", + " file_data = file_data.convert('L') # перевод в градации серого\n", + " test_img = np.array(file_data)\n", + "\n", + " # вывод собственного изображения\n", + " plt.imshow(test_img, cmap=plt.get_cmap('gray'))\n", + " plt.show()\n", + "\n", + " # предобработка\n", + " test_img = test_img / 255\n", + " test_img = np.reshape(test_img, (1,28,28,1))\n", + "\n", + " # распознавание\n", + " result = model.predict(test_img)\n", + " print('I think it\\'s', np.argmax(result))" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "mgrihPd61E8w" + }, + "source": [ + "### 10) Сравнение с моделью из предыдущей лабораторной работы\n", + "\n", + "Загружаем сохраненную полносвязную нейронную сеть из лабораторной работы №1 и оцениваем ее производительность на тех же тестовых данных для последующего сравнения." + ] + }, + { + "cell_type": "code", + "execution_count": 11, + "metadata": { + "id": "DblXqn3l1FL2" + }, + "outputs": [ + { + "data": { + "text/html": [ + "
Model: \"sequential\"\n",
+              "
\n" + ], + "text/plain": [ + "\u001b[1mModel: \"sequential\"\u001b[0m\n" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "text/html": [ + "
┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓\n",
+              "┃ Layer (type)                    ┃ Output Shape           ┃       Param # ┃\n",
+              "┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩\n",
+              "│ dense (Dense)                   │ (None, 10)             │         7,850 │\n",
+              "└─────────────────────────────────┴────────────────────────┴───────────────┘\n",
+              "
\n" + ], + "text/plain": [ + "┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓\n", + "┃\u001b[1m \u001b[0m\u001b[1mLayer (type) \u001b[0m\u001b[1m \u001b[0m┃\u001b[1m \u001b[0m\u001b[1mOutput Shape \u001b[0m\u001b[1m \u001b[0m┃\u001b[1m \u001b[0m\u001b[1m Param #\u001b[0m\u001b[1m \u001b[0m┃\n", + "┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩\n", + "│ dense (\u001b[38;5;33mDense\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m10\u001b[0m) │ \u001b[38;5;34m7,850\u001b[0m │\n", + "└─────────────────────────────────┴────────────────────────┴───────────────┘\n" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "text/html": [ + "
 Total params: 7,852 (30.68 KB)\n",
+              "
\n" + ], + "text/plain": [ + "\u001b[1m Total params: \u001b[0m\u001b[38;5;34m7,852\u001b[0m (30.68 KB)\n" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "text/html": [ + "
 Trainable params: 7,850 (30.66 KB)\n",
+              "
\n" + ], + "text/plain": [ + "\u001b[1m Trainable params: \u001b[0m\u001b[38;5;34m7,850\u001b[0m (30.66 KB)\n" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "text/html": [ + "
 Non-trainable params: 0 (0.00 B)\n",
+              "
\n" + ], + "text/plain": [ + "\u001b[1m Non-trainable params: \u001b[0m\u001b[38;5;34m0\u001b[0m (0.00 B)\n" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "text/html": [ + "
 Optimizer params: 2 (12.00 B)\n",
+              "
\n" + ], + "text/plain": [ + "\u001b[1m Optimizer params: \u001b[0m\u001b[38;5;34m2\u001b[0m (12.00 B)\n" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], + "source": [ + "model_lr1 = keras.models.load_model(\"best_mnist_model.keras\")\n", + "\n", + "model_lr1.summary()" + ] + }, + { + "cell_type": "code", + "execution_count": 12, + "metadata": { + "id": "0ki8fhJrEyEt" + }, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Shape of transformed X train: (60000, 784)\n", + "Shape of transformed X train: (10000, 784)\n", + "Shape of transformed y train: (60000, 10)\n", + "Shape of transformed y test: (10000, 10)\n" + ] + } + ], + "source": [ + "# Подготовка данных для полносвязной сети (преобразование изображений в векторы)\n", + "X_train, X_test, y_train, y_test = train_test_split(X, y,\n", + " test_size = 10000,\n", + " train_size = 60000,\n", + " random_state = 3)\n", + "num_pixels = X_train.shape[1] * X_train.shape[2]\n", + "X_train = X_train.reshape(X_train.shape[0], num_pixels) / 255\n", + "X_test = X_test.reshape(X_test.shape[0], num_pixels) / 255\n", + "print('Shape of transformed X train:', X_train.shape)\n", + "print('Shape of transformed X train:', X_test.shape)\n", + "\n", + "# Преобразование меток в формат one-hot encoding\n", + "y_train = keras.utils.to_categorical(y_train, num_classes)\n", + "y_test = keras.utils.to_categorical(y_test, num_classes)\n", + "print('Shape of transformed y train:', y_train.shape)\n", + "print('Shape of transformed y test:', y_test.shape)" + ] + }, + { + "cell_type": "code", + "execution_count": 13, + "metadata": { + "id": "0Yj0fzLNE12k" + }, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "\u001b[1m 34/313\u001b[0m \u001b[32m━━\u001b[0m\u001b[37m━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9142 - loss: 0.2983 " + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "WARNING: All log messages before absl::InitializeLog() is called are written to STDERR\n", + "I0000 00:00:1765125204.514834 271959 service.cc:145] XLA service 0x7f89bb2d4be0 initialized for platform Host (this does not guarantee that XLA will be used). Devices:\n", + "I0000 00:00:1765125204.514897 271959 service.cc:153] StreamExecutor device (0): Host, Default Version\n", + "2025-12-07 19:33:24.515300: I tensorflow/core/platform/cpu_feature_guard.cc:210] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations.\n", + "To enable the following instructions: AVX2 FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags.\n", + "2025-12-07 19:33:24.542060: I tensorflow/compiler/mlir/tensorflow/utils/dump_mlir_util.cc:268] disabling MLIR crash reproducer, set env var `MLIR_CRASH_REPRODUCER_DIRECTORY` to enable.\n", + "I0000 00:00:1765125204.640642 271959 device_compiler.h:188] Compiled cluster using XLA! This line is logged at most once for the lifetime of the process.\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "\u001b[1m313/313\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 2ms/step - accuracy: 0.9233 - loss: 0.2863\n", + "Loss on test data: 0.28625616431236267\n", + "Accuracy on test data: 0.92330002784729\n" + ] + } + ], + "source": [ + "# Оценка качества работы обученной модели на тестовой выборке\n", + "scores = model_lr1.evaluate(X_test, y_test)\n", + "print('Loss on test data:', scores[0])\n", + "print('Accuracy on test data:', scores[1])" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "MsM3ew3d1FYq" + }, + "source": [ + "### 11) Сравнительный анализ моделей\n", + "\n", + "Сравниваем сверточную нейронную сеть с полносвязной сетью по ключевым показателям: количеству параметров, времени обучения и качеству классификации." + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "xxFO4CXbIG88" + }, + "source": [ + "Таблица1:" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "xvoivjuNFlEf" + }, + "source": [ + "| Модель | Количество настраиваемых параметров | Количество эпох обучения | Качество классификации тестовой выборки |\n", + "|----------|-------------------------------------|---------------------------|-----------------------------------------|\n", + "| Сверточная | 34 826 | 15 | accuracy: 0.988; loss: 0.041 |\n", + "| Полносвязная | 7 852 | 50 | accuracy: 0.923; loss: 0.286 |\n" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "YctF8h_sIB-P" + }, + "source": [ + "**Выводы:**\n", + "\n", + "На основе проведенного анализа можно заключить, что сверточная нейронная сеть демонстрирует существенные преимущества перед полносвязной сетью при решении задач распознавания изображений:\n", + "\n", + "1. **Эффективность параметров**: Сверточная сеть имеет больше параметров (34 826 против 7 852), но при этом показывает значительно лучшие результаты, что говорит о более эффективном использовании параметров для извлечения пространственных признаков.\n", + "\n", + "2. **Скорость обучения**: Для достижения высокого качества сверточной сети требуется в 3.3 раза меньше эпох обучения (15 против 50), что существенно сокращает время обучения.\n", + "\n", + "3. **Точность классификации**: Сверточная сеть показывает более высокую точность (98.8% против 92.3%) и значительно меньшую функцию потерь (0.041 против 0.286). Разница в точности составляет 6.5%, что является существенным улучшением.\n", + "\n", + "4. **Обобщающая способность**: Сверточная сеть демонстрирует лучшую способность к обобщению, что видно из более низкой функции потерь на тестовых данных.\n", + "\n", + "Эти результаты подтверждают, что архитектура сверточных сетей, учитывающая пространственную структуру изображений через операции свертки и пулинга, является более подходящим выбором для задач компьютерного зрения, несмотря на большее количество параметров." + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "wCLHZPGB1F1y" + }, + "source": [ + "## Задание 2" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "DUOYls124TT8" + }, + "source": [ + "### В новом блокноте выполнили п. 2–8 задания 1, изменив набор данных MNIST на CIFAR-10, содержащий размеченные цветные изображения объектов, разделенные на 10 классов. \n", + "### При этом:\n", + "### - в п. 3 разбиение данных на обучающие и тестовые произвели в соотношении 50 000:10 000\n", + "### - после разбиения данных (между п. 3 и 4) вывели 25 изображений из обучающей выборки с подписями классов\n", + "### - в п. 7 одно из тестовых изображений должно распознаваться корректно, а другое – ошибочно. " + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "XDStuSpEJa8o" + }, + "source": [ + "### 1) Загрузка датасета CIFAR-10\n", + "\n", + "Загружаем набор данных CIFAR-10, который содержит цветные изображения размером 32x32 пикселя, разделенные на 10 классов: самолет, автомобиль, птица, кошка, олень, собака, лягушка, лошадь, корабль, грузовик." + ] + }, + { + "cell_type": "code", + "execution_count": 14, + "metadata": { + "id": "y0qK7eKL4Tjy" + }, + "outputs": [], + "source": [ + "# Импорт и загрузка датасета MNIST\n", + "from keras.datasets import cifar10\n", + "\n", + "(X_train, y_train), (X_test, y_test) = cifar10.load_data()" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "wTHiBy-ZJ5oh" + }, + "source": [ + "### 2) Разделение данных на обучающую и тестовую выборки\n", + "\n", + "Создаем собственное разбиение датасета CIFAR-10 в соотношении 50 000:10 000. Используем random_state = 3 для воспроизводимости результатов (k = 1 - номер нашей бригады)." + ] + }, + { + "cell_type": "code", + "execution_count": 15, + "metadata": { + "id": "DlnFbQogKD2v" + }, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Shape of X train: (50000, 32, 32, 3)\n", + "Shape of y train: (50000, 1)\n", + "Shape of X test: (10000, 32, 32, 3)\n", + "Shape of y test: (10000, 1)\n" + ] + } + ], + "source": [ + "# Создание собственного разбиения датасета\n", + "\n", + "# Объединение исходных обучающей и тестовой выборок в единый набор\n", + "X = np.concatenate((X_train, X_test))\n", + "y = np.concatenate((y_train, y_test))\n", + "\n", + "# Разделение на обучающую и тестовую выборки согласно заданию\n", + "X_train, X_test, y_train, y_test = train_test_split(X, y,\n", + " test_size = 10000,\n", + " train_size = 50000,\n", + " random_state = 3)\n", + "# Вывод размерностей полученных массивов\n", + "print('Shape of X train:', X_train.shape)\n", + "print('Shape of y train:', y_train.shape)\n", + "print('Shape of X test:', X_test.shape)\n", + "print('Shape of y test:', y_test.shape)" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "pj3bMaz1KZ3a" + }, + "source": [ + "### Визуализация примеров из обучающей выборки\n", + "\n", + "Отображаем сетку из 25 изображений из обучающей выборки с подписями соответствующих классов для визуального ознакомления с данными." + ] + }, + { + "cell_type": "code", + "execution_count": 16, + "metadata": { + "id": "TW8D67KEKhVE" + }, + "outputs": [ + { + "data": { + "image/png": "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", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], + "source": [ + "class_names = ['airplane', 'automobile', 'bird', 'cat', 'deer',\n", + " 'dog', 'frog', 'horse', 'ship', 'truck']\n", + "\n", + "plt.figure(figsize=(10,10))\n", + "for i in range(25):\n", + " plt.subplot(5,5,i+1)\n", + " plt.xticks([])\n", + " plt.yticks([])\n", + " plt.grid(False)\n", + " plt.imshow(X_train[i])\n", + " plt.xlabel(class_names[y_train[i][0]])\n", + "plt.show()" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "d3TPr2w1KQTK" + }, + "source": [ + "### 3) Предобработка данных CIFAR-10\n", + "\n", + "Нормализуем значения пикселей и преобразуем метки в формат one-hot encoding для работы с категориальной функцией потерь." + ] + }, + { + "cell_type": "code", + "execution_count": 17, + "metadata": { + "id": "iFDpxEauLZ8j" + }, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Shape of transformed X train: (50000, 32, 32, 3)\n", + "Shape of transformed X test: (10000, 32, 32, 3)\n", + "Shape of transformed y train: (50000, 10)\n", + "Shape of transformed y test: (10000, 10)\n" + ] + } + ], + "source": [ + "# Определение параметров данных и модели\n", + "num_classes = 10\n", + "input_shape = (32, 32, 3)\n", + "\n", + "# Нормализация значений пикселей: приведение к диапазону [0, 1]\n", + "X_train = X_train / 255\n", + "X_test = X_test / 255\n", + "\n", + "print('Shape of transformed X train:', X_train.shape)\n", + "print('Shape of transformed X test:', X_test.shape)\n", + "\n", + "# Преобразование меток в формат one-hot encoding\n", + "y_train = keras.utils.to_categorical(y_train, num_classes)\n", + "y_test = keras.utils.to_categorical(y_test, num_classes)\n", + "print('Shape of transformed y train:', y_train.shape)\n", + "print('Shape of transformed y test:', y_test.shape)" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "ydNITXptLeGT" + }, + "source": [ + "### 4) Построение и обучение сверточной сети для CIFAR-10\n", + "\n", + "Создаем более сложную архитектуру сверточной сети с использованием батч-нормализации и нескольких блоков свертки для работы с цветными изображениями." + ] + }, + { + "cell_type": "code", + "execution_count": 18, + "metadata": { + "id": "YhAD5CllLlv7" + }, + "outputs": [ + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/Library/Frameworks/Python.framework/Versions/3.11/lib/python3.11/site-packages/keras/src/layers/convolutional/base_conv.py:113: UserWarning: Do not pass an `input_shape`/`input_dim` argument to a layer. When using Sequential models, prefer using an `Input(shape)` object as the first layer in the model instead.\n", + " super().__init__(activity_regularizer=activity_regularizer, **kwargs)\n" + ] + }, + { + "data": { + "text/html": [ + "
Model: \"sequential_1\"\n",
+              "
\n" + ], + "text/plain": [ + "\u001b[1mModel: \"sequential_1\"\u001b[0m\n" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "text/html": [ + "
┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓\n",
+              "┃ Layer (type)                    ┃ Output Shape           ┃       Param # ┃\n",
+              "┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩\n",
+              "│ conv2d_2 (Conv2D)               │ (None, 32, 32, 32)     │           896 │\n",
+              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+              "│ batch_normalization             │ (None, 32, 32, 32)     │           128 │\n",
+              "│ (BatchNormalization)            │                        │               │\n",
+              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+              "│ conv2d_3 (Conv2D)               │ (None, 32, 32, 32)     │         9,248 │\n",
+              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+              "│ batch_normalization_1           │ (None, 32, 32, 32)     │           128 │\n",
+              "│ (BatchNormalization)            │                        │               │\n",
+              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+              "│ max_pooling2d_2 (MaxPooling2D)  │ (None, 16, 16, 32)     │             0 │\n",
+              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+              "│ dropout_1 (Dropout)             │ (None, 16, 16, 32)     │             0 │\n",
+              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+              "│ conv2d_4 (Conv2D)               │ (None, 16, 16, 64)     │        18,496 │\n",
+              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+              "│ batch_normalization_2           │ (None, 16, 16, 64)     │           256 │\n",
+              "│ (BatchNormalization)            │                        │               │\n",
+              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+              "│ conv2d_5 (Conv2D)               │ (None, 16, 16, 64)     │        36,928 │\n",
+              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+              "│ batch_normalization_3           │ (None, 16, 16, 64)     │           256 │\n",
+              "│ (BatchNormalization)            │                        │               │\n",
+              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+              "│ max_pooling2d_3 (MaxPooling2D)  │ (None, 8, 8, 64)       │             0 │\n",
+              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+              "│ dropout_2 (Dropout)             │ (None, 8, 8, 64)       │             0 │\n",
+              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+              "│ conv2d_6 (Conv2D)               │ (None, 8, 8, 128)      │        73,856 │\n",
+              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+              "│ batch_normalization_4           │ (None, 8, 8, 128)      │           512 │\n",
+              "│ (BatchNormalization)            │                        │               │\n",
+              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+              "│ conv2d_7 (Conv2D)               │ (None, 8, 8, 128)      │       147,584 │\n",
+              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+              "│ batch_normalization_5           │ (None, 8, 8, 128)      │           512 │\n",
+              "│ (BatchNormalization)            │                        │               │\n",
+              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+              "│ max_pooling2d_4 (MaxPooling2D)  │ (None, 4, 4, 128)      │             0 │\n",
+              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+              "│ dropout_3 (Dropout)             │ (None, 4, 4, 128)      │             0 │\n",
+              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+              "│ flatten_1 (Flatten)             │ (None, 2048)           │             0 │\n",
+              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+              "│ dense_1 (Dense)                 │ (None, 128)            │       262,272 │\n",
+              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+              "│ dropout_4 (Dropout)             │ (None, 128)            │             0 │\n",
+              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+              "│ dense_2 (Dense)                 │ (None, 10)             │         1,290 │\n",
+              "└─────────────────────────────────┴────────────────────────┴───────────────┘\n",
+              "
\n" + ], + "text/plain": [ + "┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓\n", + "┃\u001b[1m \u001b[0m\u001b[1mLayer (type) \u001b[0m\u001b[1m \u001b[0m┃\u001b[1m \u001b[0m\u001b[1mOutput Shape \u001b[0m\u001b[1m \u001b[0m┃\u001b[1m \u001b[0m\u001b[1m Param #\u001b[0m\u001b[1m \u001b[0m┃\n", + "┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩\n", + "│ conv2d_2 (\u001b[38;5;33mConv2D\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m32\u001b[0m, \u001b[38;5;34m32\u001b[0m, \u001b[38;5;34m32\u001b[0m) │ \u001b[38;5;34m896\u001b[0m │\n", + "├─────────────────────────────────┼────────────────────────┼───────────────┤\n", + "│ batch_normalization │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m32\u001b[0m, \u001b[38;5;34m32\u001b[0m, \u001b[38;5;34m32\u001b[0m) │ \u001b[38;5;34m128\u001b[0m │\n", + "│ (\u001b[38;5;33mBatchNormalization\u001b[0m) │ │ │\n", + "├─────────────────────────────────┼────────────────────────┼───────────────┤\n", + "│ conv2d_3 (\u001b[38;5;33mConv2D\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m32\u001b[0m, \u001b[38;5;34m32\u001b[0m, \u001b[38;5;34m32\u001b[0m) │ \u001b[38;5;34m9,248\u001b[0m │\n", + "├─────────────────────────────────┼────────────────────────┼───────────────┤\n", + "│ batch_normalization_1 │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m32\u001b[0m, \u001b[38;5;34m32\u001b[0m, \u001b[38;5;34m32\u001b[0m) │ \u001b[38;5;34m128\u001b[0m │\n", + "│ (\u001b[38;5;33mBatchNormalization\u001b[0m) │ │ │\n", + "├─────────────────────────────────┼────────────────────────┼───────────────┤\n", + "│ max_pooling2d_2 (\u001b[38;5;33mMaxPooling2D\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m16\u001b[0m, \u001b[38;5;34m16\u001b[0m, \u001b[38;5;34m32\u001b[0m) │ \u001b[38;5;34m0\u001b[0m │\n", + "├─────────────────────────────────┼────────────────────────┼───────────────┤\n", + "│ dropout_1 (\u001b[38;5;33mDropout\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m16\u001b[0m, \u001b[38;5;34m16\u001b[0m, \u001b[38;5;34m32\u001b[0m) │ \u001b[38;5;34m0\u001b[0m │\n", + "├─────────────────────────────────┼────────────────────────┼───────────────┤\n", + "│ conv2d_4 (\u001b[38;5;33mConv2D\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m16\u001b[0m, \u001b[38;5;34m16\u001b[0m, \u001b[38;5;34m64\u001b[0m) │ \u001b[38;5;34m18,496\u001b[0m │\n", + "├─────────────────────────────────┼────────────────────────┼───────────────┤\n", + "│ batch_normalization_2 │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m16\u001b[0m, \u001b[38;5;34m16\u001b[0m, \u001b[38;5;34m64\u001b[0m) │ \u001b[38;5;34m256\u001b[0m │\n", + "│ (\u001b[38;5;33mBatchNormalization\u001b[0m) │ │ │\n", + "├─────────────────────────────────┼────────────────────────┼───────────────┤\n", + "│ conv2d_5 (\u001b[38;5;33mConv2D\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m16\u001b[0m, \u001b[38;5;34m16\u001b[0m, \u001b[38;5;34m64\u001b[0m) │ \u001b[38;5;34m36,928\u001b[0m │\n", + "├─────────────────────────────────┼────────────────────────┼───────────────┤\n", + "│ batch_normalization_3 │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m16\u001b[0m, \u001b[38;5;34m16\u001b[0m, \u001b[38;5;34m64\u001b[0m) │ \u001b[38;5;34m256\u001b[0m │\n", + "│ (\u001b[38;5;33mBatchNormalization\u001b[0m) │ │ │\n", + "├─────────────────────────────────┼────────────────────────┼───────────────┤\n", + "│ max_pooling2d_3 (\u001b[38;5;33mMaxPooling2D\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m8\u001b[0m, \u001b[38;5;34m8\u001b[0m, \u001b[38;5;34m64\u001b[0m) │ \u001b[38;5;34m0\u001b[0m │\n", + "├─────────────────────────────────┼────────────────────────┼───────────────┤\n", + "│ dropout_2 (\u001b[38;5;33mDropout\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m8\u001b[0m, \u001b[38;5;34m8\u001b[0m, \u001b[38;5;34m64\u001b[0m) │ \u001b[38;5;34m0\u001b[0m │\n", + "├─────────────────────────────────┼────────────────────────┼───────────────┤\n", + "│ conv2d_6 (\u001b[38;5;33mConv2D\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m8\u001b[0m, \u001b[38;5;34m8\u001b[0m, \u001b[38;5;34m128\u001b[0m) │ \u001b[38;5;34m73,856\u001b[0m │\n", + "├─────────────────────────────────┼────────────────────────┼───────────────┤\n", + "│ batch_normalization_4 │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m8\u001b[0m, \u001b[38;5;34m8\u001b[0m, \u001b[38;5;34m128\u001b[0m) │ \u001b[38;5;34m512\u001b[0m │\n", + "│ (\u001b[38;5;33mBatchNormalization\u001b[0m) │ │ │\n", + "├─────────────────────────────────┼────────────────────────┼───────────────┤\n", + "│ conv2d_7 (\u001b[38;5;33mConv2D\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m8\u001b[0m, \u001b[38;5;34m8\u001b[0m, \u001b[38;5;34m128\u001b[0m) │ \u001b[38;5;34m147,584\u001b[0m │\n", + "├─────────────────────────────────┼────────────────────────┼───────────────┤\n", + "│ batch_normalization_5 │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m8\u001b[0m, \u001b[38;5;34m8\u001b[0m, \u001b[38;5;34m128\u001b[0m) │ \u001b[38;5;34m512\u001b[0m │\n", + "│ (\u001b[38;5;33mBatchNormalization\u001b[0m) │ │ │\n", + "├─────────────────────────────────┼────────────────────────┼───────────────┤\n", + "│ max_pooling2d_4 (\u001b[38;5;33mMaxPooling2D\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m4\u001b[0m, \u001b[38;5;34m4\u001b[0m, \u001b[38;5;34m128\u001b[0m) │ \u001b[38;5;34m0\u001b[0m │\n", + "├─────────────────────────────────┼────────────────────────┼───────────────┤\n", + "│ dropout_3 (\u001b[38;5;33mDropout\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m4\u001b[0m, \u001b[38;5;34m4\u001b[0m, \u001b[38;5;34m128\u001b[0m) │ \u001b[38;5;34m0\u001b[0m │\n", + "├─────────────────────────────────┼────────────────────────┼───────────────┤\n", + "│ flatten_1 (\u001b[38;5;33mFlatten\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m2048\u001b[0m) │ \u001b[38;5;34m0\u001b[0m │\n", + "├─────────────────────────────────┼────────────────────────┼───────────────┤\n", + "│ dense_1 (\u001b[38;5;33mDense\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m128\u001b[0m) │ \u001b[38;5;34m262,272\u001b[0m │\n", + "├─────────────────────────────────┼────────────────────────┼───────────────┤\n", + "│ dropout_4 (\u001b[38;5;33mDropout\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m128\u001b[0m) │ \u001b[38;5;34m0\u001b[0m │\n", + "├─────────────────────────────────┼────────────────────────┼───────────────┤\n", + "│ dense_2 (\u001b[38;5;33mDense\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m10\u001b[0m) │ \u001b[38;5;34m1,290\u001b[0m │\n", + "└─────────────────────────────────┴────────────────────────┴───────────────┘\n" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "text/html": [ + "
 Total params: 552,362 (2.11 MB)\n",
+              "
\n" + ], + "text/plain": [ + "\u001b[1m Total params: \u001b[0m\u001b[38;5;34m552,362\u001b[0m (2.11 MB)\n" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "text/html": [ + "
 Trainable params: 551,466 (2.10 MB)\n",
+              "
\n" + ], + "text/plain": [ + "\u001b[1m Trainable params: \u001b[0m\u001b[38;5;34m551,466\u001b[0m (2.10 MB)\n" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "text/html": [ + "
 Non-trainable params: 896 (3.50 KB)\n",
+              "
\n" + ], + "text/plain": [ + "\u001b[1m Non-trainable params: \u001b[0m\u001b[38;5;34m896\u001b[0m (3.50 KB)\n" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], + "source": [ + "# Создание модели сверточной нейронной сети\n", + "model = Sequential()\n", + "\n", + "# Блок 1\n", + "model.add(layers.Conv2D(32, (3, 3), padding=\"same\",\n", + " activation=\"relu\", input_shape=input_shape))\n", + "model.add(layers.BatchNormalization())\n", + "model.add(layers.Conv2D(32, (3, 3), padding=\"same\", activation=\"relu\"))\n", + "model.add(layers.BatchNormalization())\n", + "model.add(layers.MaxPooling2D((2, 2)))\n", + "model.add(layers.Dropout(0.25))\n", + "\n", + "# Блок 2\n", + "model.add(layers.Conv2D(64, (3, 3), padding=\"same\", activation=\"relu\"))\n", + "model.add(layers.BatchNormalization())\n", + "model.add(layers.Conv2D(64, (3, 3), padding=\"same\", activation=\"relu\"))\n", + "model.add(layers.BatchNormalization())\n", + "model.add(layers.MaxPooling2D((2, 2)))\n", + "model.add(layers.Dropout(0.25))\n", + "\n", + "# Блок 3\n", + "model.add(layers.Conv2D(128, (3, 3), padding=\"same\", activation=\"relu\"))\n", + "model.add(layers.BatchNormalization())\n", + "model.add(layers.Conv2D(128, (3, 3), padding=\"same\", activation=\"relu\"))\n", + "model.add(layers.BatchNormalization())\n", + "model.add(layers.MaxPooling2D((2, 2)))\n", + "model.add(layers.Dropout(0.4))\n", + "\n", + "model.add(layers.Flatten())\n", + "model.add(layers.Dense(128, activation='relu'))\n", + "model.add(layers.Dropout(0.5))\n", + "model.add(layers.Dense(num_classes, activation=\"softmax\"))\n", + "\n", + "\n", + "model.summary()" + ] + }, + { + "cell_type": "code", + "execution_count": 19, + "metadata": { + "id": "3otvqMjjOdq5" + }, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Epoch 1/50\n", + "\u001b[1m704/704\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m214s\u001b[0m 295ms/step - accuracy: 0.3409 - loss: 1.8087 - val_accuracy: 0.4302 - val_loss: 1.6950\n", + "Epoch 2/50\n", + "\u001b[1m704/704\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m210s\u001b[0m 299ms/step - accuracy: 0.5008 - loss: 1.3835 - val_accuracy: 0.6096 - val_loss: 1.1257\n", + "Epoch 3/50\n", + "\u001b[1m704/704\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m209s\u001b[0m 297ms/step - accuracy: 0.5871 - loss: 1.1704 - val_accuracy: 0.6310 - val_loss: 1.1089\n", + "Epoch 4/50\n", + "\u001b[1m704/704\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m205s\u001b[0m 291ms/step - accuracy: 0.6421 - loss: 1.0381 - val_accuracy: 0.6666 - val_loss: 0.9580\n", + "Epoch 5/50\n", + "\u001b[1m704/704\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m195s\u001b[0m 277ms/step - accuracy: 0.6788 - loss: 0.9402 - val_accuracy: 0.7004 - val_loss: 0.8947\n", + "Epoch 6/50\n", + "\u001b[1m704/704\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m160s\u001b[0m 227ms/step - accuracy: 0.7065 - loss: 0.8630 - val_accuracy: 0.6856 - val_loss: 0.9637\n", + "Epoch 7/50\n", + "\u001b[1m704/704\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m159s\u001b[0m 226ms/step - accuracy: 0.7256 - loss: 0.8078 - val_accuracy: 0.7604 - val_loss: 0.6995\n", + "Epoch 8/50\n", + "\u001b[1m704/704\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m159s\u001b[0m 225ms/step - accuracy: 0.7458 - loss: 0.7463 - val_accuracy: 0.7388 - val_loss: 0.7766\n", + "Epoch 9/50\n", + "\u001b[1m704/704\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m160s\u001b[0m 227ms/step - accuracy: 0.7601 - loss: 0.7104 - val_accuracy: 0.7420 - val_loss: 0.7523\n", + "Epoch 10/50\n", + "\u001b[1m704/704\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m159s\u001b[0m 226ms/step - accuracy: 0.7770 - loss: 0.6658 - val_accuracy: 0.7782 - val_loss: 0.6714\n", + "Epoch 11/50\n", + "\u001b[1m704/704\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m196s\u001b[0m 278ms/step - accuracy: 0.7876 - loss: 0.6321 - val_accuracy: 0.7852 - val_loss: 0.6610\n", + "Epoch 12/50\n", + "\u001b[1m704/704\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m179s\u001b[0m 254ms/step - accuracy: 0.7978 - loss: 0.6006 - val_accuracy: 0.8026 - val_loss: 0.5872\n", + "Epoch 13/50\n", + "\u001b[1m704/704\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m179s\u001b[0m 254ms/step - accuracy: 0.8073 - loss: 0.5754 - val_accuracy: 0.7994 - val_loss: 0.5945\n", + "Epoch 14/50\n", + "\u001b[1m704/704\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m179s\u001b[0m 254ms/step - accuracy: 0.8146 - loss: 0.5536 - val_accuracy: 0.7776 - val_loss: 0.6921\n", + "Epoch 15/50\n", + "\u001b[1m704/704\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m179s\u001b[0m 254ms/step - accuracy: 0.8226 - loss: 0.5308 - val_accuracy: 0.8016 - val_loss: 0.6051\n", + "Epoch 16/50\n", + "\u001b[1m704/704\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m173s\u001b[0m 246ms/step - accuracy: 0.8295 - loss: 0.5097 - val_accuracy: 0.8082 - val_loss: 0.6001\n", + "Epoch 17/50\n", + "\u001b[1m704/704\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m162s\u001b[0m 231ms/step - accuracy: 0.8333 - loss: 0.4900 - val_accuracy: 0.8204 - val_loss: 0.5621\n", + "Epoch 18/50\n", + "\u001b[1m704/704\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m175s\u001b[0m 248ms/step - accuracy: 0.8399 - loss: 0.4763 - val_accuracy: 0.8202 - val_loss: 0.5716\n", + "Epoch 19/50\n", + "\u001b[1m704/704\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m199s\u001b[0m 283ms/step - accuracy: 0.8458 - loss: 0.4535 - val_accuracy: 0.8132 - val_loss: 0.5784\n", + "Epoch 20/50\n", + "\u001b[1m704/704\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m179s\u001b[0m 254ms/step - accuracy: 0.8494 - loss: 0.4406 - val_accuracy: 0.8276 - val_loss: 0.5378\n", + "Epoch 21/50\n", + "\u001b[1m704/704\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m177s\u001b[0m 251ms/step - accuracy: 0.8536 - loss: 0.4293 - val_accuracy: 0.8132 - val_loss: 0.5989\n", + "Epoch 22/50\n", + "\u001b[1m704/704\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m174s\u001b[0m 248ms/step - accuracy: 0.8591 - loss: 0.4120 - val_accuracy: 0.8398 - val_loss: 0.5143\n", + "Epoch 23/50\n", + "\u001b[1m704/704\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m183s\u001b[0m 260ms/step - accuracy: 0.8610 - loss: 0.4031 - val_accuracy: 0.8216 - val_loss: 0.5681\n", + "Epoch 24/50\n", + "\u001b[1m704/704\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m179s\u001b[0m 254ms/step - accuracy: 0.8668 - loss: 0.3945 - val_accuracy: 0.8358 - val_loss: 0.5374\n", + "Epoch 25/50\n", + "\u001b[1m704/704\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m180s\u001b[0m 256ms/step - accuracy: 0.8708 - loss: 0.3810 - val_accuracy: 0.8166 - val_loss: 0.6225\n", + "Epoch 26/50\n", + "\u001b[1m704/704\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m181s\u001b[0m 257ms/step - accuracy: 0.8706 - loss: 0.3787 - val_accuracy: 0.8380 - val_loss: 0.5285\n", + "Epoch 27/50\n", + "\u001b[1m704/704\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m182s\u001b[0m 259ms/step - accuracy: 0.8771 - loss: 0.3634 - val_accuracy: 0.8410 - val_loss: 0.5138\n", + "Epoch 28/50\n", + "\u001b[1m704/704\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m177s\u001b[0m 251ms/step - accuracy: 0.8776 - loss: 0.3538 - val_accuracy: 0.8280 - val_loss: 0.5548\n", + "Epoch 29/50\n", + "\u001b[1m704/704\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m168s\u001b[0m 238ms/step - accuracy: 0.8824 - loss: 0.3486 - val_accuracy: 0.8390 - val_loss: 0.5372\n", + "Epoch 30/50\n", + "\u001b[1m704/704\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m173s\u001b[0m 246ms/step - accuracy: 0.8838 - loss: 0.3398 - val_accuracy: 0.8434 - val_loss: 0.4986\n", + "Epoch 31/50\n", + "\u001b[1m704/704\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m183s\u001b[0m 260ms/step - accuracy: 0.8876 - loss: 0.3322 - val_accuracy: 0.8380 - val_loss: 0.5392\n", + "Epoch 32/50\n", + "\u001b[1m704/704\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m185s\u001b[0m 262ms/step - accuracy: 0.8899 - loss: 0.3235 - val_accuracy: 0.8086 - val_loss: 0.6294\n", + "Epoch 33/50\n", + "\u001b[1m704/704\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m191s\u001b[0m 271ms/step - accuracy: 0.8931 - loss: 0.3156 - val_accuracy: 0.8430 - val_loss: 0.5467\n", + "Epoch 34/50\n", + "\u001b[1m704/704\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m179s\u001b[0m 254ms/step - accuracy: 0.8920 - loss: 0.3133 - val_accuracy: 0.8454 - val_loss: 0.5099\n", + "Epoch 35/50\n", + "\u001b[1m704/704\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m181s\u001b[0m 256ms/step - accuracy: 0.8965 - loss: 0.3024 - val_accuracy: 0.8468 - val_loss: 0.5167\n", + "Epoch 36/50\n", + "\u001b[1m704/704\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m180s\u001b[0m 256ms/step - accuracy: 0.8956 - loss: 0.3030 - val_accuracy: 0.8296 - val_loss: 0.5907\n", + "Epoch 37/50\n", + "\u001b[1m704/704\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m181s\u001b[0m 257ms/step - accuracy: 0.8980 - loss: 0.2956 - val_accuracy: 0.8426 - val_loss: 0.5412\n", + "Epoch 38/50\n", + "\u001b[1m704/704\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m181s\u001b[0m 257ms/step - accuracy: 0.9006 - loss: 0.2887 - val_accuracy: 0.8438 - val_loss: 0.5187\n", + "Epoch 39/50\n", + "\u001b[1m704/704\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m179s\u001b[0m 254ms/step - accuracy: 0.9013 - loss: 0.2874 - val_accuracy: 0.8478 - val_loss: 0.5139\n", + "Epoch 40/50\n", + "\u001b[1m704/704\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m179s\u001b[0m 254ms/step - accuracy: 0.9029 - loss: 0.2824 - val_accuracy: 0.8068 - val_loss: 0.6571\n", + "Epoch 41/50\n", + "\u001b[1m704/704\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m179s\u001b[0m 254ms/step - accuracy: 0.9062 - loss: 0.2758 - val_accuracy: 0.8542 - val_loss: 0.5129\n", + "Epoch 42/50\n", + "\u001b[1m704/704\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m180s\u001b[0m 255ms/step - accuracy: 0.9060 - loss: 0.2727 - val_accuracy: 0.8538 - val_loss: 0.4998\n", + "Epoch 43/50\n", + "\u001b[1m704/704\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m187s\u001b[0m 265ms/step - accuracy: 0.9096 - loss: 0.2650 - val_accuracy: 0.8504 - val_loss: 0.4944\n", + "Epoch 44/50\n", + "\u001b[1m704/704\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m179s\u001b[0m 254ms/step - accuracy: 0.9100 - loss: 0.2646 - val_accuracy: 0.8480 - val_loss: 0.5352\n", + "Epoch 45/50\n", + "\u001b[1m704/704\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m175s\u001b[0m 249ms/step - accuracy: 0.9109 - loss: 0.2560 - val_accuracy: 0.8510 - val_loss: 0.5218\n", + "Epoch 46/50\n", + "\u001b[1m704/704\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m177s\u001b[0m 252ms/step - accuracy: 0.9130 - loss: 0.2518 - val_accuracy: 0.8552 - val_loss: 0.4983\n", + "Epoch 47/50\n", + "\u001b[1m704/704\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m181s\u001b[0m 257ms/step - accuracy: 0.9124 - loss: 0.2525 - val_accuracy: 0.8578 - val_loss: 0.5095\n", + "Epoch 48/50\n", + "\u001b[1m704/704\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m177s\u001b[0m 251ms/step - accuracy: 0.9161 - loss: 0.2456 - val_accuracy: 0.8488 - val_loss: 0.5426\n", + "Epoch 49/50\n", + "\u001b[1m704/704\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m174s\u001b[0m 247ms/step - accuracy: 0.9171 - loss: 0.2449 - val_accuracy: 0.8530 - val_loss: 0.5429\n", + "Epoch 50/50\n", + "\u001b[1m704/704\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m197s\u001b[0m 280ms/step - accuracy: 0.9195 - loss: 0.2354 - val_accuracy: 0.8454 - val_loss: 0.5250\n" + ] + }, + { + "data": { + "text/plain": [ + "" + ] + }, + "execution_count": 19, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "# Компиляция и обучение модели\n", + "batch_size = 64\n", + "epochs = 50\n", + "model.compile(loss=\"categorical_crossentropy\", optimizer=\"adam\", metrics=[\"accuracy\"])\n", + "model.fit(X_train, y_train, batch_size=batch_size, epochs=epochs, validation_split=0.1)" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "Vv1kUHWTLl9B" + }, + "source": [ + "### 5) Оценка качества модели на тестовых данных\n", + "\n", + "Оцениваем финальную производительность обученной модели на тестовой выборке CIFAR-10." + ] + }, + { + "cell_type": "code", + "execution_count": 20, + "metadata": { + "id": "SaDxydiyLmRX" + }, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "\u001b[1m313/313\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m12s\u001b[0m 38ms/step - accuracy: 0.8539 - loss: 0.5047\n", + "Loss on test data: 0.5046958327293396\n", + "Accuracy on test data: 0.8539000153541565\n" + ] + } + ], + "source": [ + "# Оценка качества работы обученной модели на тестовой выборке\n", + "scores = model.evaluate(X_test, y_test)\n", + "print('Loss on test data:', scores[0])\n", + "print('Accuracy on test data:', scores[1])" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "OdgEiyUGLmhP" + }, + "source": [ + "### 6) Демонстрация работы модели на отдельных примерах\n", + "\n", + "Визуализируем результаты распознавания для двух тестовых изображений: одно должно быть распознано корректно, другое - ошибочно." + ] + }, + { + "cell_type": "code", + "execution_count": 32, + "metadata": { + "id": "t3yGj1MlLm9H" + }, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 114ms/step\n", + "NN output: [[1.1500329e-13 1.3227661e-13 1.2523241e-10 1.1334410e-10 7.6330755e-13\n", + " 2.6473241e-14 1.0000000e+00 7.4253257e-18 1.0440019e-13 2.6218085e-13]]\n" + ] + }, + { + "data": { + "image/png": "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", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Real mark: 6\n", + "NN answer: 6\n", + "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 98ms/step\n", + "NN output: [[2.0177353e-09 1.4144381e-12 9.2603455e-05 1.9454856e-04 2.1098103e-02\n", + " 9.7849804e-01 2.5194169e-05 9.1513859e-05 3.2438701e-11 4.6777016e-10]]\n" + ] + }, + { + "data": { + "image/png": "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", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Real mark: 4\n", + "NN answer: 5\n" + ] + } + ], + "source": [ + "# Визуализация результатов распознавания для двух тестовых изображений\n", + "\n", + "for n in [3,14]:\n", + " result = model.predict(X_test[n:n+1])\n", + " print('NN output:', result)\n", + "\n", + " plt.imshow(X_test[n].reshape(32,32,3), cmap=plt.get_cmap('gray'))\n", + " plt.show()\n", + " print('Real mark: ', np.argmax(y_test[n]))\n", + " print('NN answer: ', np.argmax(result))" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "3h6VGDRrLnNC" + }, + "source": [ + "### 7) Детальный анализ качества классификации CIFAR-10\n", + "\n", + "Генерируем подробный отчет о качестве классификации и строим матрицу ошибок для анализа работы модели по каждому классу." + ] + }, + { + "cell_type": "code", + "execution_count": 22, + "metadata": { + "id": "od56oyyzM0nw" + }, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "\u001b[1m313/313\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m11s\u001b[0m 35ms/step\n", + " precision recall f1-score support\n", + "\n", + " airplane 0.84 0.91 0.87 1007\n", + " automobile 0.95 0.91 0.93 1037\n", + " bird 0.83 0.79 0.81 1030\n", + " cat 0.77 0.65 0.70 990\n", + " deer 0.83 0.82 0.82 966\n", + " dog 0.72 0.83 0.77 1009\n", + " frog 0.90 0.89 0.89 972\n", + " horse 0.87 0.89 0.88 991\n", + " ship 0.95 0.92 0.93 990\n", + " truck 0.89 0.93 0.91 1008\n", + "\n", + " accuracy 0.85 10000\n", + " macro avg 0.86 0.85 0.85 10000\n", + "weighted avg 0.86 0.85 0.85 10000\n", + "\n" + ] + }, + { + "data": { + "image/png": "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", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], + "source": [ + "# Получение истинных и предсказанных меток для всех тестовых данных\n", + "true_labels = np.argmax(y_test, axis=1)\n", + "\n", + "predicted_labels = np.argmax(model.predict(X_test), axis=1)\n", + "\n", + "# Вывод подробного отчета о качестве классификации\n", + "print(classification_report(true_labels, predicted_labels, target_names=class_names))\n", + "# Построение и визуализация матрицы ошибок\n", + "conf_matrix = confusion_matrix(true_labels, predicted_labels)\n", + "\n", + "fig, ax = plt.subplots(figsize=(6, 6))\n", + "disp = ConfusionMatrixDisplay(confusion_matrix=conf_matrix,display_labels=class_names)\n", + "disp.plot(ax=ax, xticks_rotation=45) # поворот подписей по X и приятная палитра\n", + "plt.tight_layout() # чтобы всё влезло\n", + "plt.show()" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "RF4xK1cxamBc" + }, + "source": [ + "**Выводы по результатам классификации CIFAR-10:**\n", + "\n", + "Разработанная сверточная нейронная сеть показала хорошие результаты при классификации цветных изображений из датасета CIFAR-10. Модель достигла точности классификации около 86%, что является достойным результатом для данной задачи, учитывая сложность различения объектов в низком разрешении (32x32 пикселя) и наличие 10 различных классов.\n", + "\n", + "Использование батч-нормализации и dropout-регуляризации позволило улучшить обобщающую способность модели и предотвратить переобучение. Архитектура с тремя блоками сверточных слоев эффективно извлекает иерархические признаки из изображений, что подтверждается полученными метриками качества." + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [] + } + ], + "metadata": { + "accelerator": "GPU", + "colab": { + "gpuType": "T4", + "provenance": [] + }, + "kernelspec": { + "display_name": "Python 3", + "name": "python3" + }, + "language_info": { + "codemirror_mode": { + "name": "ipython", + "version": 3 + }, + "file_extension": ".py", + "mimetype": "text/x-python", + "name": "python", + "nbconvert_exporter": "python", + "pygments_lexer": "ipython3", + "version": "3.11.9" + } + }, + "nbformat": 4, + "nbformat_minor": 0 +} diff --git a/labworks/LW3/report_new.md b/labworks/LW3/report_new.md new file mode 100644 index 0000000..f73f6f4 --- /dev/null +++ b/labworks/LW3/report_new.md @@ -0,0 +1,612 @@ +# Отчёт по лабораторной работе №3 + +**Троянов Д.С., Чернов Д.Е. — А-01-22** + +--- + +## Задание 1 + +### 1) Подготовка рабочей среды и импорт библиотек + +Инициализируем рабочую среду и подключаем необходимые библиотеки для работы с нейронными сетями и обработки данных. Также настраиваем SSL для корректной загрузки датасетов. + +```python +# Подключение необходимых библиотек и модулей +import os +import ssl + +# Обход проблемы с SSL сертификатами на macOS +ssl._create_default_https_context = ssl._create_unverified_context + +# Для работы в Google Colab раскомментируйте следующую строку: +# os.chdir('/content/drive/MyDrive/Colab Notebooks/is_lab3') + +from tensorflow import keras +from tensorflow.keras import layers +from tensorflow.keras.models import Sequential +import matplotlib.pyplot as plt +import numpy as np +from sklearn.metrics import classification_report, confusion_matrix +from sklearn.metrics import ConfusionMatrixDisplay +``` + +### 2) Загрузка датасета MNIST + +Загружаем стандартный набор данных MNIST, который содержит изображения рукописных цифр от 0 до 9 с соответствующими метками. + +```python +# Импорт и загрузка датасета MNIST +from keras.datasets import mnist +(X_train, y_train), (X_test, y_test) = mnist.load_data() +``` + +### 3) Разделение данных на обучающую и тестовую выборки + +Производим собственное разбиение датасета в соотношении 60 000:10 000. Для воспроизводимости результатов используем параметр random_state = 3 (вычисляется как 4k - 1, где k = 1 - номер нашей бригады). Выводим размерности полученных массивов данных. + +```python +# Создание собственного разбиения датасета +from sklearn.model_selection import train_test_split + +# Объединение исходных обучающей и тестовой выборок в единый набор +X = np.concatenate((X_train, X_test)) +y = np.concatenate((y_train, y_test)) + +# Разделение на обучающую и тестовую выборки согласно заданию +X_train, X_test, y_train, y_test = train_test_split(X, y, + test_size = 10000, + train_size = 60000, + random_state = 3) +# Вывод размерностей полученных массивов +print('Shape of X train:', X_train.shape) +print('Shape of y train:', y_train.shape) +print('Shape of X test:', X_test.shape) +print('Shape of y test:', y_test.shape) +``` +``` +Shape of X train: (60000, 28, 28) +Shape of y train: (60000,) +Shape of X test: (10000, 28, 28) +Shape of y test: (10000,) +``` + +### 4) Предобработка данных + +Выполняем нормализацию пикселей изображений (приведение к диапазону [0, 1]) и преобразование меток в формат one-hot encoding для корректной работы с категориальной функцией потерь. Выводим размерности предобработанных массивов данных. + +```python +# Определение параметров данных и модели +num_classes = 10 +input_shape = (28, 28, 1) + +# Нормализация значений пикселей: приведение к диапазону [0, 1] +X_train = X_train / 255 +X_test = X_test / 255 + +# Добавление размерности канала для корректной работы с Conv2D слоями +# Преобразование из (высота, ширина) в (высота, ширина, каналы) +X_train = np.expand_dims(X_train, -1) +X_test = np.expand_dims(X_test, -1) +print('Shape of transformed X train:', X_train.shape) +print('Shape of transformed X test:', X_test.shape) + +# Преобразование меток в формат one-hot encoding +y_train = keras.utils.to_categorical(y_train, num_classes) +y_test = keras.utils.to_categorical(y_test, num_classes) +print('Shape of transformed y train:', y_train.shape) +print('Shape of transformed y test:', y_test.shape) +``` +``` +Shape of transformed X train: (60000, 28, 28, 1) +Shape of transformed X test: (10000, 28, 28, 1) +Shape of transformed y train: (60000, 10) +Shape of transformed y test: (10000, 10) +``` + +### 5) Построение и обучение сверточной нейронной сети + +Создаем архитектуру сверточной нейронной сети с использованием сверточных слоев, пулинга и регуляризации. Обучаем модель на подготовленных данных с выделением части данных для валидации. Выводим информацию об архитектуре нейронной сети. + +```python +# Создание модели сверточной нейронной сети +model = Sequential() +model.add(layers.Conv2D(32, kernel_size=(3, 3), activation="relu", input_shape=input_shape)) +model.add(layers.MaxPooling2D(pool_size=(2, 2))) +model.add(layers.Conv2D(64, kernel_size=(3, 3), activation="relu")) +model.add(layers.MaxPooling2D(pool_size=(2, 2))) +model.add(layers.Dropout(0.5)) +model.add(layers.Flatten()) +model.add(layers.Dense(num_classes, activation="softmax")) + +model.summary() +``` +**Model: "sequential"** +| Layer (type) | Output Shape | Param # | +|--------------------------------|---------------------|--------:| +| conv2d (Conv2D) | (None, 26, 26, 32) | 320 | +| max_pooling2d (MaxPooling2D) | (None, 13, 13, 32) | 0 | +| conv2d_1 (Conv2D) | (None, 11, 11, 64) | 18,496 | +| max_pooling2d_1 (MaxPooling2D) | (None, 5, 5, 64) | 0 | +| dropout (Dropout) | (None, 5, 5, 64) | 0 | +| flatten (Flatten) | (None, 1600) | 0 | +| dense (Dense) | (None, 10) | 16,010 | +**Total params:** 34,826 (136.04 KB) +**Trainable params:** 34,826 (136.04 KB) +**Non-trainable params:** 0 (0.00 B) + +```python +# Компиляция и обучение модели +batch_size = 512 +epochs = 15 +model.compile(loss="categorical_crossentropy", optimizer="adam", metrics=["accuracy"]) +model.fit(X_train, y_train, batch_size=batch_size, epochs=epochs, validation_split=0.1) +``` + +### 6) Оценка качества модели на тестовых данных + +Проводим финальную оценку обученной модели на независимой тестовой выборке, получая значения функции потерь и точности классификации. + +```python +# Оценка качества работы обученной модели на тестовой выборке +scores = model.evaluate(X_test, y_test) +print('Loss on test data:', scores[0]) +print('Accuracy on test data:', scores[1]) +``` +``` +313/313 ━━━━━━━━━━━━━━━━━━━━ 1s 4ms/step - accuracy: 0.9884 - loss: 0.0409 +Loss on test data: 0.04092026501893997 +Accuracy on test data: 0.9883999824523926 +``` + +### 7) Демонстрация работы модели на отдельных примерах + +Визуализируем результаты распознавания для двух тестовых изображений, сравнивая предсказания модели с истинными метками. + +```python +# Визуализация результатов распознавания для двух тестовых изображений + +for n in [3,26]: + result = model.predict(X_test[n:n+1]) + print('NN output:', result) + + plt.imshow(X_test[n].reshape(28,28), cmap=plt.get_cmap('gray')) + plt.show() + print('Real mark: ', np.argmax(y_test[n])) + print('NN answer: ', np.argmax(result)) +``` +![MNIST тестовое изображение - цифра 6](images/1.png) +``` +Real mark: 6 +NN answer: 6 +``` +![MNIST тестовое изображение - цифра 3](images/2.png) +``` +Real mark: 3 +NN answer: 3 +``` + +### 8) Детальный анализ качества классификации + +Генерируем подробный отчет о качестве классификации и строим матрицу ошибок для визуального анализа работы модели по каждому классу. + +```python +# Получение истинных и предсказанных меток для всех тестовых данных +true_labels = np.argmax(y_test, axis=1) +# Предсказанные метки классов +predicted_labels = np.argmax(model.predict(X_test), axis=1) + +# Вывод подробного отчета о качестве классификации +print(classification_report(true_labels, predicted_labels)) +# Построение и визуализация матрицы ошибок +conf_matrix = confusion_matrix(true_labels, predicted_labels) +# Отрисовка матрицы ошибок в виде "тепловой карты" +display = ConfusionMatrixDisplay(confusion_matrix=conf_matrix) +display.plot() +plt.show() +``` +``` +313/313 ━━━━━━━━━━━━━━━━━━━━ 2s 5ms/step + precision recall f1-score support + + 0 1.00 0.99 1.00 1001 + 1 0.99 1.00 0.99 1143 + 2 0.99 0.99 0.99 987 + 3 0.99 0.99 0.99 1023 + 4 0.99 0.99 0.99 974 + 5 1.00 0.98 0.99 907 + 6 0.99 0.99 0.99 974 + 7 0.98 0.99 0.99 1032 + 8 0.98 0.98 0.98 1006 + 9 0.98 0.99 0.98 953 + + accuracy 0.99 10000 + macro avg 0.99 0.99 0.99 10000 +weighted avg 0.99 0.99 0.99 10000 +``` +![Матрица ошибок для MNIST](images/3.png) + +### 9) Тестирование на собственных изображениях + +Загружаем и обрабатываем собственные изображения цифр, созданные ранее, и проверяем способность модели их корректно распознавать. + +```python +# Загрузка и обработка собственных изображений +from PIL import Image + +for name_image in ['2.png', '7.png']: + file_data = Image.open(name_image) + file_data = file_data.convert('L') # Перевод в градации серого + test_img = np.array(file_data) + + # Вывод собственного изображения + plt.imshow(test_img, cmap=plt.get_cmap('gray')) + plt.show() + + # Предобработка + test_img = test_img / 255 + test_img = np.reshape(test_img, (1,28,28,1)) + + # Распознавание + result = model.predict(test_img) + print('I think it\'s', np.argmax(result)) +``` +![Собственное изображение - цифра 2](images/4.png) +``` +I think it's 2 +``` +![Собственное изображение - цифра 7](images/5.png) +``` +I think it's 7 +``` + +### 10) Сравнение с моделью из предыдущей лабораторной работы + +Загружаем сохраненную полносвязную нейронную сеть из лабораторной работы №1 и оцениваем ее производительность на тех же тестовых данных для последующего сравнения. + +```python +model_lr1 = keras.models.load_model("best_mnist_model.keras") + +model_lr1.summary() +``` +**Model: "sequential"** +| Layer (type) | Output Shape | Param # | +|------------------|-------------:|--------:| +| dense (Dense) | (None, 10) | 7,850 | +**Total params:** 7,852 (30.68 KB) +**Trainable params:** 7,850 (30.66 KB) +**Non-trainable params:** 0 (0.00 B) +**Optimizer params:** 2 (12.00 B) + + +```python +# Подготовка данных для полносвязной сети (преобразование изображений в векторы) +X_train, X_test, y_train, y_test = train_test_split(X, y, + test_size = 10000, + train_size = 60000, + random_state = 3) +num_pixels = X_train.shape[1] * X_train.shape[2] +X_train = X_train.reshape(X_train.shape[0], num_pixels) / 255 +X_test = X_test.reshape(X_test.shape[0], num_pixels) / 255 +print('Shape of transformed X train:', X_train.shape) +print('Shape of transformed X train:', X_test.shape) + +# Преобразование меток в формат one-hot encoding +y_train = keras.utils.to_categorical(y_train, num_classes) +y_test = keras.utils.to_categorical(y_test, num_classes) +print('Shape of transformed y train:', y_train.shape) +print('Shape of transformed y test:', y_test.shape) +``` +``` +Shape of transformed X train: (60000, 784) +Shape of transformed X train: (10000, 784) +Shape of transformed y train: (60000, 10) +Shape of transformed y test: (10000, 10) +``` + +```python +# Оценка качества работы модели на тестовых данных +scores = model_lr1.evaluate(X_test, y_test) +print('Loss on test data:', scores[0]) +print('Accuracy on test data:', scores[1]) +``` +``` +313/313 ━━━━━━━━━━━━━━━━━━━━ 1s 3ms/step - accuracy: 0.9233 - loss: 0.2863 +Loss on test data: 0.28625616431236267 +Accuracy on test data: 0.92330002784729 +``` + +### 11) Сравнительный анализ моделей + +Сравниваем сверточную нейронную сеть с полносвязной сетью по ключевым показателям: количеству параметров, времени обучения и качеству классификации. Делаем выводы по результатам применения сверточной нейронной сети для распознавания изображений. + +**Таблица сравнения моделей:** + +| Модель | Количество настраиваемых параметров | Количество эпох обучения | Качество классификации тестовой выборки | +|----------|-------------------------------------|---------------------------|-----------------------------------------| +| Сверточная | 34 826 | 15 | accuracy: 0.988; loss: 0.041 | +| Полносвязная | 7 852 | 50 | accuracy: 0.923; loss: 0.286 | + + +**Выводы:** + +На основе проведенного анализа можно заключить, что сверточная нейронная сеть демонстрирует существенные преимущества перед полносвязной сетью при решении задач распознавания изображений: + +1. **Эффективность параметров**: Сверточная сеть имеет больше параметров (34 826 против 7 852), но при этом показывает значительно лучшие результаты, что говорит о более эффективном использовании параметров для извлечения пространственных признаков. + +2. **Скорость обучения**: Для достижения высокого качества сверточной сети требуется в 3.3 раза меньше эпох обучения (15 против 50), что существенно сокращает время обучения. + +3. **Точность классификации**: Сверточная сеть показывает более высокую точность (98.8% против 92.3%) и значительно меньшую функцию потерь (0.041 против 0.286). Разница в точности составляет 6.5 процентных пункта, что является существенным улучшением. + +4. **Обобщающая способность**: Сверточная сеть демонстрирует лучшую способность к обобщению, что видно из более низкой функции потерь на тестовых данных. + +Эти результаты подтверждают, что архитектура сверточных сетей, учитывающая пространственную структуру изображений через операции свертки и пулинга, является более подходящим выбором для задач компьютерного зрения, несмотря на большее количество параметров. + +## Задание 2 + +### Работа с датасетом CIFAR-10 + +Повторяем основные этапы задания 1, но используем датасет CIFAR-10, содержащий цветные изображения объектов 10 различных классов. + +Особенности выполнения: +- Разделение данных производится в соотношении 50 000:10 000 +- После разделения визуализируем 25 изображений из обучающей выборки +- При демонстрации работы модели выбираем примеры так, чтобы одно изображение распознавалось корректно, а другое - ошибочно + +### 1) Загрузка датасета CIFAR-10 + +Загружаем набор данных CIFAR-10, который содержит цветные изображения размером 32x32 пикселя, разделенные на 10 классов: самолет, автомобиль, птица, кошка, олень, собака, лягушка, лошадь, корабль, грузовик. + +```python +# Импорт и загрузка датасета CIFAR-10 +from keras.datasets import cifar10 + +(X_train, y_train), (X_test, y_test) = cifar10.load_data() +``` + +### 2) Разделение данных на обучающую и тестовую выборки + +Создаем собственное разбиение датасета CIFAR-10 в соотношении 50 000:10 000. Используем random_state = 3 для воспроизводимости результатов (k = 1 - номер нашей бригады). Выводим размерности полученных массивов данных. + +```python +# Создание собственного разбиения датасета + +# Объединение исходных выборок +X = np.concatenate((X_train, X_test)) +y = np.concatenate((y_train, y_test)) + +# Разделение на обучающую и тестовую выборки +X_train, X_test, y_train, y_test = train_test_split(X, y, + test_size = 10000, + train_size = 50000, + random_state = 3) +# Вывод размерностей +print('Shape of X train:', X_train.shape) +print('Shape of y train:', y_train.shape) +print('Shape of X test:', X_test.shape) +print('Shape of y test:', y_test.shape) +``` +``` +Shape of X train: (50000, 32, 32, 3) +Shape of y train: (50000, 1) +Shape of X test: (10000, 32, 32, 3) +Shape of y test: (10000, 1) +``` + +### Визуализация примеров из обучающей выборки + +Отображаем сетку из 25 изображений из обучающей выборки с подписями соответствующих классов для визуального ознакомления с данными. + +```python +class_names = ['airplane', 'automobile', 'bird', 'cat', 'deer', + 'dog', 'frog', 'horse', 'ship', 'truck'] + +plt.figure(figsize=(10,10)) +for i in range(25): + plt.subplot(5,5,i+1) + plt.xticks([]) + plt.yticks([]) + plt.grid(False) + plt.imshow(X_train[i]) + plt.xlabel(class_names[y_train[i][0]]) +plt.show() +``` +![Сетка из 25 изображений CIFAR-10](images/6.png) + +### 3) Предобработка данных CIFAR-10 + +Нормализуем значения пикселей и преобразуем метки в формат one-hot encoding для работы с категориальной функцией потерь. Выводим размерности предобработанных массивов данных. + +```python +# Определение параметров данных и модели +num_classes = 10 +input_shape = (32, 32, 3) + +# Нормализация значений пикселей: приведение к диапазону [0, 1] +X_train = X_train / 255 +X_test = X_test / 255 + +print('Shape of transformed X train:', X_train.shape) +print('Shape of transformed X test:', X_test.shape) + +# Преобразование меток в формат one-hot encoding +y_train = keras.utils.to_categorical(y_train, num_classes) +y_test = keras.utils.to_categorical(y_test, num_classes) +print('Shape of transformed y train:', y_train.shape) +print('Shape of transformed y test:', y_test.shape) +``` +``` +Shape of transformed X train: (50000, 32, 32, 3) +Shape of transformed X test: (10000, 32, 32, 3) +Shape of transformed y train: (50000, 10) +Shape of transformed y test: (10000, 10) +``` + +### 4) Построение и обучение сверточной сети для CIFAR-10 + +Создаем более сложную архитектуру сверточной сети с использованием батч-нормализации и нескольких блоков свертки для работы с цветными изображениями. Обучаем модель на подготовленных данных с выделением части данных для валидации. + +```python +# Создание модели сверточной нейронной сети +model = Sequential() + +# Блок 1 +model.add(layers.Conv2D(32, (3, 3), padding="same", + activation="relu", input_shape=input_shape)) +model.add(layers.BatchNormalization()) +model.add(layers.Conv2D(32, (3, 3), padding="same", activation="relu")) +model.add(layers.BatchNormalization()) +model.add(layers.MaxPooling2D((2, 2))) +model.add(layers.Dropout(0.25)) + +# Блок 2 +model.add(layers.Conv2D(64, (3, 3), padding="same", activation="relu")) +model.add(layers.BatchNormalization()) +model.add(layers.Conv2D(64, (3, 3), padding="same", activation="relu")) +model.add(layers.BatchNormalization()) +model.add(layers.MaxPooling2D((2, 2))) +model.add(layers.Dropout(0.25)) + +# Блок 3 +model.add(layers.Conv2D(128, (3, 3), padding="same", activation="relu")) +model.add(layers.BatchNormalization()) +model.add(layers.Conv2D(128, (3, 3), padding="same", activation="relu")) +model.add(layers.BatchNormalization()) +model.add(layers.MaxPooling2D((2, 2))) +model.add(layers.Dropout(0.4)) + +model.add(layers.Flatten()) +model.add(layers.Dense(128, activation='relu')) +model.add(layers.Dropout(0.5)) +model.add(layers.Dense(num_classes, activation="softmax")) + + +model.summary() +``` +**Model: "sequential_9"** +| Layer (type) | Output Shape | Param # | +|--------------------------------------------|-------------------|---------:| +| conv2d_41 (Conv2D) | (None, 32, 32, 32) | 896 | +| batch_normalization_6 (BatchNormalization) | (None, 32, 32, 32) | 128 | +| conv2d_42 (Conv2D) | (None, 32, 32, 32) | 9,248 | +| batch_normalization_7 (BatchNormalization) | (None, 32, 32, 32) | 128 | +| max_pooling2d_26 (MaxPooling2D) | (None, 16, 16, 32) | 0 | +| dropout_24 (Dropout) | (None, 16, 16, 32) | 0 | +| conv2d_43 (Conv2D) | (None, 16, 16, 64) | 18,496 | +| batch_normalization_8 (BatchNormalization) | (None, 16, 16, 64) | 256 | +| conv2d_44 (Conv2D) | (None, 16, 16, 64) | 36,928 | +| batch_normalization_9 (BatchNormalization) | (None, 16, 16, 64) | 256 | +| max_pooling2d_27 (MaxPooling2D) | (None, 8, 8, 64) | 0 | +| dropout_25 (Dropout) | (None, 8, 8, 64) | 0 | +| conv2d_45 (Conv2D) | (None, 8, 8, 128) | 73,856 | +| batch_normalization_10 (BatchNormalization)| (None, 8, 8, 128) | 512 | +| conv2d_46 (Conv2D) | (None, 8, 8, 128) | 147,584 | +| batch_normalization_11 (BatchNormalization)| (None, 8, 8, 128) | 512 | +| max_pooling2d_28 (MaxPooling2D) | (None, 4, 4, 128) | 0 | +| dropout_26 (Dropout) | (None, 4, 4, 128) | 0 | +| flatten_9 (Flatten) | (None, 2048) | 0 | +| dense_17 (Dense) | (None, 128) | 262,272 | +| dropout_27 (Dropout) | (None, 128) | 0 | +| dense_18 (Dense) | (None, 10) | 1,290 | +**Total params:** 552,362 (2.11 MB) +**Trainable params:** 551,466 (2.10 MB) +**Non-trainable params:** 896 (3.50 KB) + +```python +# Компиляция и обучение модели +batch_size = 64 +epochs = 50 +model.compile(loss="categorical_crossentropy", optimizer="adam", metrics=["accuracy"]) +model.fit(X_train, y_train, batch_size=batch_size, epochs=epochs, validation_split=0.1) +``` + +### 5) Оценка качества модели на тестовых данных + +Оцениваем финальную производительность обученной модели на тестовой выборке CIFAR-10. + +```python +# Оценка качества работы модели на тестовых данных +scores = model.evaluate(X_test, y_test) +print('Loss on test data:', scores[0]) +print('Accuracy on test data:', scores[1]) +``` +``` +313/313 ━━━━━━━━━━━━━━━━━━━━ 7s 22ms/step - accuracy: 0.8553 - loss: 0.5210 +Loss on test data: 0.5209607481956482 +Accuracy on test data: 0.8553000092506409 +``` + +### 6) Демонстрация работы модели на отдельных примерах + +Визуализируем результаты распознавания для двух тестовых изображений: одно должно быть распознано корректно, другое - ошибочно. + +```python +# Визуализация результатов распознавания для двух тестовых изображений + +for n in [3,14]: + result = model.predict(X_test[n:n+1]) + print('NN output:', result) + + plt.imshow(X_test[n].reshape(32,32,3), cmap=plt.get_cmap('gray')) + plt.show() + print('Real mark: ', np.argmax(y_test[n])) + print('NN answer: ', np.argmax(result)) +``` +![CIFAR-10 тестовое изображение](images/7.png) +``` +Real mark: 6 +NN answer: 6 +``` +![CIFAR-10 тестовое изображение - олень (ошибочно распознано)](images/8.png) +``` +Real mark: 4 +NN answer: 5 +``` + +### 7) Детальный анализ качества классификации CIFAR-10 + +Генерируем подробный отчет о качестве классификации и строим матрицу ошибок для анализа работы модели по каждому классу. + +```python +# Получение истинных и предсказанных меток для всех тестовых данных +true_labels = np.argmax(y_test, axis=1) +# Предсказанные метки классов +predicted_labels = np.argmax(model.predict(X_test), axis=1) + +# Вывод подробного отчета о качестве классификации +print(classification_report(true_labels, predicted_labels, target_names=class_names)) +# Построение и визуализация матрицы ошибок +conf_matrix = confusion_matrix(true_labels, predicted_labels) +# Отрисовка матрицы ошибок в виде "тепловой карты" +fig, ax = plt.subplots(figsize=(6, 6)) +disp = ConfusionMatrixDisplay(confusion_matrix=conf_matrix,display_labels=class_names) +disp.plot(ax=ax, xticks_rotation=45) # Поворот подписей по X и приятная палитра +plt.tight_layout() # Чтобы всё влезло +plt.show() +``` +``` +313/313 ━━━━━━━━━━━━━━━━━━━━ 1s 4ms/step + precision recall f1-score support + + airplane 0.84 0.91 0.87 1007 + automobile 0.95 0.91 0.93 1037 + bird 0.83 0.79 0.81 1030 + cat 0.77 0.65 0.70 990 + deer 0.83 0.82 0.82 966 + dog 0.72 0.83 0.77 1009 + frog 0.90 0.89 0.89 972 + horse 0.87 0.89 0.88 991 + ship 0.95 0.92 0.93 990 + truck 0.89 0.93 0.91 1008 + + accuracy 0.85 10000 + macro avg 0.86 0.85 0.85 10000 +weighted avg 0.86 0.85 0.85 10000 +``` +![Матрица ошибок для CIFAR-10](images/9.png) + +**Выводы по результатам классификации CIFAR-10:** + +Разработанная сверточная нейронная сеть показала хорошие результаты при классификации цветных изображений из датасета CIFAR-10. Модель достигла точности классификации 85.5% (accuracy: 0.855, loss: 0.521) на тестовой выборке, а в детальном отчете о классификации показала accuracy 0.85, что является достойным результатом для данной задачи, учитывая сложность различения объектов в низком разрешении (32x32 пикселя) и наличие 10 различных классов. + +Использование батч-нормализации и dropout-регуляризации позволило улучшить обобщающую способность модели и предотвратить переобучение. Архитектура с тремя блоками сверточных слоев эффективно извлекает иерархические признаки из изображений, что подтверждается полученными метриками качества. +